Dissertations / Theses on the topic 'Video content analysis'

Video Content Analysis (VCA) is usually computationally intense and time consuming. In this thesis the efficiency of VCA is increased by implementing a distributed VCA architecture. Automatic speech recognition is used as a case study to evaluate how the efficiency of VCA can be increased by distributing the workload across several machines. The system is to be run on standard desktop computers and need to support a variety of operating systems. The developed distributed system is compared to a serial system in use today. The results show increased performance, at the cost of a small increase in error rate. Two types of load balancing algorithms, static load balancing and dynamic load balancing, is evaluated in order to increase system throughput and it is concluded that the dynamic algorithm outperforms the static algorithm when running on a heterogeneous set of machines and that the differences are negligible when running on a homogeneous set of machines.

The networks of surveillance cameras installed in public places and private territories continuously record video data with the aim of detecting and preventing unlawful activities. This enhances the importance of video content analysis applications, either for real time (i.e. analytic) or post-event (i.e. forensic) analysis. In this thesis, the primary focus is on four key aspects of video content analysis, namely; 1. Moving object detection and recognition, 2. Correction of colours in the video frames and recognition of colours of moving objects, 3. Make and model recognition of vehicles and identification of their type, 4. Detection and recognition of text information in outdoor scenes. To address the first issue, a framework is presented in the first part of the thesis that efficiently detects and recognizes moving objects in videos. The framework targets the problem of object detection in the presence of complex background. The object detection part of the framework relies on background modelling technique and a novel post processing step where the contours of the foreground regions (i.e. moving object) are refined by the classification of edge segments as belonging either to the background or to the foreground region. Further, a novel feature descriptor is devised for the classification of moving objects into humans, vehicles and background. The proposed feature descriptor captures the texture information present in the silhouette of foreground objects. To address the second issue, a framework for the correction and recognition of true colours of objects in videos is presented with novel noise reduction, colour enhancement and colour recognition stages. The colour recognition stage makes use of temporal information to reliably recognize the true colours of moving objects in multiple frames. The proposed framework is specifically designed to perform robustly on videos that have poor quality because of surrounding illumination, camera sensor imperfection and artefacts due to high compression. In the third part of the thesis, a framework for vehicle make and model recognition and type identification is presented. As a part of this work, a novel feature representation technique for distinctive representation of vehicle images has emerged. The feature representation technique uses dense feature description and mid-level feature encoding scheme to capture the texture in the frontal view of the vehicles. The proposed method is insensitive to minor in-plane rotation and skew within the image. The capability of the proposed framework can be enhanced to any number of vehicle classes without re-training. Another important contribution of this work is the publication of a comprehensive up to date dataset of vehicle images to support future research in this domain. The problem of text detection and recognition in images is addressed in the last part of the thesis. A novel technique is proposed that exploits the colour information in the image for the identification of text regions. Apart from detection, the colour information is also used to segment characters from the words. The recognition of identified characters is performed using shape features and supervised learning. Finally, a lexicon based alignment procedure is adopted to finalize the recognition of strings present in word images. Extensive experiments have been conducted on benchmark datasets to analyse the performance of proposed algorithms. The results show that the proposed moving object detection and recognition technique superseded well-know baseline techniques. The proposed framework for the correction and recognition of object colours in video frames achieved all the aforementioned goals. The performance analysis of the vehicle make and model recognition framework on multiple datasets has shown the strength and reliability of the technique when used within various scenarios. Finally, the experimental results for the text detection and recognition framework on benchmark datasets have revealed the potential of the proposed scheme for accurate detection and recognition of text in the wild.

Due to scientific advances in mobility and connectivity, digital media can be distributed to multiple platforms by streams and video on demand services. The abundance of video productions poses a problem in term sof storage, organization and cataloging. How the movies or TV-series should be sorted and retrieved is much dictated by user preferences,motivating proper indexing and an notation of video content. While movies tend to be described by keywords or genre, this thesis constitutesan attempt to automatically index videos, based on their semantics. Representing a video by the sentiment it invokes, would not only be more descriptive, but could also be used to compare movies directly based onthe actual content. Since filmmaking is biased by human perception,this project looks to utilize these characteristics for machine learning.The video is modeled as a sequence of shots, attempting to capture the temporal nature of the information. Sentiment analysis of videos has been used as labels in a supervised learning algorithm, namely a SVM using a string kernel. Besides the specifics of learning, the work of this thesis involve other relevant fields such a feature extraction and videosegmentation. The results show that there are patterns in video fit for learning; however the performance of the method is inconclusive due to lack of data. It would therefore be interesting to evaluate the approach further, using more data along with minor modifications.
Tack vare tekniska framsteg inom mobilitet och tillgänglighet, kan media såsom film distribueras till flertalet olika plattformar, i form avströmning eller liknande tjänster. Det enorma utbudet av TV-serier och film utgör svårigheter för hur materialet ska lagras, sorteras och katalogiseras. Ofta är det dessutom användarna som ställer krav på vad somär relevant i en sökning. Det påvisar vikten av lämplig notation och indexering.I dag används oftast text som beskrivning av videoinnehållet, i form av antingen genre eller nyckelord. Det här arbetet är ett försök till att automatiskt kunna indexera film och serier, beroende på det semantiska innehållet. Att istället beskriva videomaterialet beroende på hur det uppfattas, samt de känslor som väcks, innebär en mer karaktäristisk skildring. Ett sådant signalement skulle beskriva det faktiska innehållet på ett annat sätt, som är mer lämpligt för jämförelser mellan två videoproduktioner. Eftersom skapandet av film anpassar sig till hur människor uppfattar videomaterial, kommer denna undersökning utnyttja de regler och praxis som används, som hjälp för maskininlärningen. Hur en film uppfattas, eller de känslor som framkallas, utgör en bas för inlärningen, då de används för att beteckna de olika koncept som ska klassificeras. En video representeras som en sekvens av klipp, med avsikt att fånga de tidsmässiga egenskaperna. Metoden som används för denna övervakade inlärning är en SVM som kan hantera data i form av strängar. Förutom de teknikaliteter som krävs för att förstå inlärningen,tar rapporten upp relevanta andra områden, t.ex. hur information ska extraheras och videosegmentering. Resultaten visar att det finns mönster i video, lämpliga för inlärning. På grund av för lite data, är det inte möjligt att avgöra hur metoden presterar. Det vore därför intressant med vidare analys, med mer data samt smärre modifikationer.

New technologies have increased the possible ways in which humans interact and as a result require new as well as old ways to establish trust. The findings of this paper suggest that trust should be divided into three main categories of trust drivers, exchange factors, design factors and motivational factors. The results indicate that tutorials can, and should, include drivers that build these categories. While we found varying degrees on how well implemented these were, we found that design factors were generally more prominent and found opportunities for tutorials to improve on the exchange side.

This thesis focuses on four main research themes namely shot boundary detection, fast frame alignment, activity-driven video summarisation, and highlights based video annotation and retrieval. A number of novel algorithms have been proposed to address these issues, which can be highlighted as follows. Firstly, accurate and robust shot boundary detection is achieved through modelling of cuts into sub-categories and appearance based modelling of several gradual transitions, along with some novel features extracted from compressed video. Secondly, fast and robust frame alignment is achieved via the proposed subspace phase correlation (SPC) and an improved sub-pixel strategy. The SPC is proved to be insensitive to zero-mean-noise, and its gradient-based extension is even robust to non-zero-mean noise and can be used to deal with non-overlapped regions for robust image registration. Thirdly, hierarchical modelling of rush videos using formal language techniques is proposed, which can guide the modelling and removal of several kinds of junk frames as well as adaptive clustering of retakes. With an extracted activity level measurement, shot and sub-shot are detected for content-adaptive video summarisation. Fourthly, highlights based video annotation and retrieval is achieved, in which statistical modelling of skin pixel colours, knowledge-based shot detection, and improved determination of camera motion patterns are employed. Within these proposed techniques, one important principle is to integrate various kinds of feature evidence and to incorporate prior knowledge in modelling the given problems. High-level hierarchical representation is extracted from the original linear structure for effective management and content-based retrieval of video data. As most of the work is implemented in the compressed domain, one additional benefit is the achieved high efficiency, which will be useful for many online applications.

Thesis: Ph. D., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2014.
Cataloged from PDF version of thesis.
Includes bibliographical references (pages 141-154).
Video data exhibits a variety of structures: pixels exhibit spatial structure, e.g., the same class of objects share certain shapes and/or colors in image; sequences of frames exhibit temporal structure, e.g., dynamic events such as jumping and running have a certain chronological order of frame occurrence; and when combined with audio and text, there is multimodal structure, e.g., human behavioral data shows correlation between audio (speech) and visual information (gesture). Identifying, formulating, and learning these structured patterns is a fundamental task in video content analysis. This thesis tackles two challenging problems in video content analysis - human action recognition and behavior understanding - and presents novel algorithms to solve each: one algorithm performs sequence classification by learning spatio-temporal structure of human action; another performs data fusion by learning multimodal structure of human behavior. The first algorithm, hierarchical sequence summarization, is a probabilistic graphical model that learns spatio-temporal structure of human action in a fine-to-coarse manner. It constructs a hierarchical representation of video by iteratively summarizing the video sequence, and uses the representation to learn spatio-temporal structure of human action, classifying sequences into action categories. We developed an efficient learning method to train our model, and show that its complexity grows only sublinearly with the depth of the hierarchy. The second algorithm focuses on data fusion - the task of combining information from multiple modalities in an effective way. Our approach is motivated by the observation that human behavioral data is modality-wise sparse, i.e., information from just a few modalities contain most information needed at any given time. We perform data fusion using structured sparsity, representing a multimodal signal as a sparse combination of multimodal basis vectors embedded in a hierarchical tree structure, learned directly from the data. The key novelty is in a mixed-norm formulation of regularized matrix factorization via structured sparsity. We show the effectiveness of our algorithms on two real-world application scenarios: recognizing aircraft handling signals used by the US Navy, and predicting people's impression about the personality of public figures from their multimodal behavior. We describe the whole procedure of the recognition pipeline, from the signal acquisition to processing, to the interpretation of the processed signals using our algorithms. Experimental results show that our algorithms outperform state-of-the-art methods on human action recognition and behavior understanding.
by Yale Song.
Ph. D.

Due to growing security concerns, video surveillance and monitoring has received an immense attention from both federal agencies and private firms. The main concern is that a single camera, even if allowed to rotate or translate, is not sufficient to cover a large area for video surveillance. A more general solution with wide range of applications is to allow the deployed cameras to have a non-overlapping field of view (FoV) and to, if possible, allow these cameras to move freely in 3D space. This thesis addresses the issue of how cameras in such a network can be calibrated and how the network as a whole can be calibrated, such that each camera as a unit in the network is aware of its orientation with respect to all the other cameras in the network. Different types of cameras might be present in a multiple camera network and novel techniques are presented for efficient calibration of these cameras. Specifically: (i) For a stationary camera, we derive new constraints on the Image of the Absolute Conic (IAC). These new constraints are shown to be intrinsic to IAC; (ii) For a scene where object shadows are cast on a ground plane, we track the shadows on the ground plane cast by at least two unknown stationary points, and utilize the tracked shadow positions to compute the horizon line and hence compute the camera intrinsic and extrinsic parameters; (iii) A novel solution to a scenario where a camera is observing pedestrians is presented. The uniqueness of formulation lies in recognizing two harmonic homologies present in the geometry obtained by observing pedestrians; (iv) For a freely moving camera, a novel practical method is proposed for its self-calibration which even allows it to change its internal parameters by zooming; and (v) due to the increased application of the pan-tilt-zoom (PTZ) cameras, a technique is presented that uses only two images to estimate five camera parameters. For an automatically configurable multi-camera network, having non-overlapping field of view and possibly containing moving cameras, a practical framework is proposed that determines the geometry of such a dynamic camera network. It is shown that only one automatically computed vanishing point and a line lying on any plane orthogonal to the vertical direction is sufficient to infer the geometry of a dynamic network. Our method generalizes previous work which considers restricted camera motions. Using minimal assumptions, we are able to successfully demonstrate promising results on synthetic as well as on real data. Applications to path modeling, GPS coordinate estimation, and configuring mixed-reality environment are explored.
Ph.D.
School of Electrical Engineering and Computer Science
Engineering and Computer Science
Computer Science PhD

In recent years, concerns over video game addiction have increased. Both individual factors (such as impulsivity and reward sensitivity) and content features in video games (such as reward and punishment features) play a role in the development of video game addiction. In the current study, a content analysis coding procedure is developed in order to categorize the reinforcement schedules of three existing commercial video games from three different genres. Our findings indicate that the reward features in the game The Mighty Quest for Epic Loot resembles a partial reinforcement schedule while the reward features in the games Team Fortress 2 and Destination Sol resemble a continuous reinforcement schedule. This key finding demonstrates that the reward content features in commercial video games can be classified along a theoretically meaningful dimensions put forth by Operant Conditioning Theory. Furthermore, in this study we pilot tested several outcome measures related to video game addiction that will be crucial to our conceptualization of video game addiction in the future including a measure of playing time, game enjoyment, trait impulsivity, a measure of behavioral impulsivity, and the game addiction scale. We found that the video game with a partial reinforcement schedule was significantly more enjoyable than the video games with a continuous reinforcement schedule.

L’objet de cette thèse est de proposer un système d’indexation semi-automatique et de recherche interactive pour la vidéo. Nous avons développé un algorithme de détection des plans automatique sans paramètre, ni seuil. Nous avons choisi un classifieur SVM pour sa capacité à traiter des caractéristiques de grandes dimensions tout en préservant des garanties de généralisation pour peu d’exemples d’apprentissage. Nous avons étudié plusieurs combinaisons de caractéristiques et de fonctions noyaux et présenté des résultats intéressants pour la tâche de détection de plan de TRECVID 2006. Nous avons proposé un système interactif de recherche de contenu vidéo : RETINVID, qui permet de réduire le nombre d’images à annoter par l’utilisateur. Ces images sont sélectionnées pour leur capacité à accroître la connaissance sur les données. Nous avons effectué de nombreuses simulations sur les données de la tâche de concepts haut-niveaux de TRECVID 2005
This thesis presents work towards a unified framework for semi-automated video indexing and interactive retrieval. To create an efficient index, a set of representative key frames are selected from the entire video content. We developed an automatic shot boundary detection algorithm to get rid of parameters and thresholds. We adopted a SVM classifier due to its ability to use very high dimensional feature spaces while at the same time keeping strong generalization guarantees from few training examples. We deeply evaluated the combination of features and kernels and present interesting results obtained, for shot extraction TRECVID 2006 Task. We then propose an interactive video retrieval system: RETINVID, to significantly reduce the number of key frames annotated by the user. The key frames are selected based on their ability to increase the knowledge of the data. We perform an experiment against the 2005 TRECVID benchmark for high-level task

La estructura de alto nivel del vídeo se puede obtener a partir de conocimiento sobre el dominio más una representación de los contenidos que proporcione información semántica. En este contexto, las representaciones de la semántica de nivel medio vienen dadas en términos de características de bajo nivel y de la información que expresan acerca de los contenidos del vídeo. Las representaciones de nivel medio permiten obtener de forma automática agrupamientos semánticamente significativos de los shots, que son posteriormente utilizados conjuntamente con conocimientos de alto nivel específicos del dominio para obtener la estructura del vídeo. En general, las representaciones de nivel medio también dependen del dominio. Los descriptores que forman parte de la representación están específicamente diseñados para una aplicación concreta, teniendo en cuenta los requisitos del dominio y el conocimiento que tenemos del mismo. En esta tesis se propone una representación de nivel medio de los contenidos videográficos que permite obtener agrupamientos de shots que son semánticamente significativos. Esta representación no depende del dominio, y sin embargo aporta la información necesaria para obtener la estructura de alto nivel del vídeo, gracias a la combinación de las contribuciones de diferentes características de bajo nivel de las imágenes a la semántica de nivel medio.
La semántica de nivel medio se encuentra implícita en las características de bajo nivel, dado que un concepto semántico concreto genera una combinación específica de valores de las mismas. El problema consiste en "tender un puente sobre el vacío" entre las características de bajo nivel que se observan y sus correspondientes conceptos semánticos de nivel medio ocultos. Para establecer relaciones entre estos dos niveles, se utilizan técnicas de visión por computador y procesamiento de imágenes. Otras disciplinas como la cinematografía y la semiótica también proporcionan pistas importantes para determinar como se usan las características de bajo nivel para crear conceptos semánticos. Una descripción adecuada de las características de bajo nivel puede proporcionar una representación de sus correspondientes contenidos semánticos. Más en concreto, el color resumido en un histograma se utiliza para representar la apariencia de los objetos. Cuando el objeto es el fondo de la escena, su color aporta información sobre la localización. De la misma manera, en esta tesis se analiza la semántica que transmite una descripción del movimiento. Las características de movimiento resumidas en una matriz de coocurrencias temporales proporcionan información sobre las operaciones de la cámara y el tipo de toma (primer plano, etc.) en función de la distancia relativa entre la cámara y los objetos filmados.
La principal contribución de esta tesis es una representación de los contenidos visuales del vídeo basada en el resumen del comportamiento dinámico de las características de bajo nivel como procesos temporales descritos por cadenas de Markov. Los estados de la cadena de Markov vienen dados por los valores observados de una característica de bajo nivel. A diferencia de las representaciones de los shots basadas en keyframes, el modelo de cadena de Markov considera información de todos los frames del shot en la misma representación. Las medidas de similitud naturales en un marco probabilístico, como la divergencia de Kullback-Leibler, pueden ser utilizadas para comparar cadenas de Markov y, por tanto, el contenido de los shots que representan. En la misma representación se pueden combinar múltiples características de las imágenes mediante el acoplamiento de sus correspondientes cadenas. Esta tesis presenta diferentes formas de acoplar cadenas de Markov, y en particular la llamada Cadenas Acopladas de Markov (Coupled Markov Chains, CMC). También se detalla un método para encontrar la estructura de acoplamiento óptima en términos de coste mínimo y mínima pérdida de información, ya que esta merma se relaciona directamente con la pérdida de precisión de la estructura acoplada para representar contenidos de vídeo. Durante el proceso de cálculo de las representaciones de los shots se detectan las fronteras entre éstos usando el mismo modelo y medidas de similitud.
Cuando las características de color y movimiento se combinan, la representación en cadenas acopladas de Markov proporciona un descriptor semántico de nivel medio que contiene información implícita sobre objetos (sus identidades, tamaños y patrones de movimiento), movimiento de cámara, localización, tipo de toma, relaciones temporales entre los elementos que componen la escena y actividad global, entendida como la cantidad de acción. Conceptos semánticos más complejos emergen de la unión de estos descriptores de nivel medio, tales como "cabeza parlante", que surge de la combinación de un primer plano con el color de la piel de la cara. Añadiendo el componente de localización en el dominio de Noticiarios, las cabezas parlantes se pueden subclasificar en "presentadores" (localizados en estudio) y "corresponsales" (localizados en exteriores). Estas y otras categorías semánticamente significativas aparecen cuando los shots representados usando el modelo CMC se agrupan de forma no supervisada. Los conceptos mejor definidos se corresponden con grupos compactos, que pueden ser detectados usando una medida de densidad. Conocimiento de alto nivel sobre el dominio se puede definir mediante simples reglas basadas en estos conceptos, que establecen fronteras en la estructura semántica del vídeo. El modelado de contenidos de vídeo por cadenas acopladas de Markov unifica los primeros pasos del proceso de análisis semántico de vídeo y proporciona una representación de nivel medio semánticamente significativa sin necesidad de detectar previamente las fronteras entre shots.
The high-level structure of a video can be obtained once we have knowledge about the domain plus a representation of the contents that provides semantic information. In this context, intermediate-level semantic representations are defined in terms of low-level features and the information they convey about the contents of the video. Intermediate-level representations allow us to obtain semantically meaningful clusterings of shots, which are then used together with high-level domain-specific knowledge in order to obtain the structure of the video. Intermediate-level representations are usually domain-dependent as well. The descriptors involved in the representation are specifically tailored for the application, taking into account the requirements of the domain and the knowledge we have about it. This thesis proposes an intermediate-level representation of video contents that allows us to obtain semantically meaningful clusterings of shots. This representation does not depend on the domain, but still provides enough information to obtain the high-level structure of the video by combining the contributions of different low-level image features to the intermediate-level semantics.
Intermediate-level semantics are implicitly supplied by low-level features, given that a specific semantic concept generates some particular combination of feature values. The problem is to bridge the gap between observed low-level features and their corresponding hidden intermediate-level semantic concepts. Computer vision and image processing techniques are used to establish relationships between them. Other disciplines such as filmmaking and semiotics also provide important clues to discover how low-level features are used to create semantic concepts. A proper descriptor of low-level features can provide a representation of their corresponding semantic contents. Particularly, color summarized as a histogram is used to represent the appearance of objects. When this object is the background, color provides information about location. In the same way, the semantics conveyed by a description of motion have been analyzed in this thesis. A summary of motion features as a temporal cooccurrence matrix provides information about camera operation and the type of shot in terms of relative distance of the camera to the subject matter.
The main contribution of this thesis is a representation of visual contents in video based on summarizing the dynamic behavior of low-level features as temporal processes described by Markov chains (MC). The states of the MC are given by the values of an observed low-level feature. Unlike keyframe-based representations of shots, information from all the frames is considered in the MC modeling. Natural similarity measures such as likelihood ratios and Kullback-Leibler divergence are used to compare MC's, and thus the contents of the shots they are representing. In this framework, multiple image features can be combined in the same representation by coupling their corresponding MC's. Different ways of coupling MC's are presented, particularly the one called Coupled Markov Chains (CMC). A method to find the optimal coupling structure in terms of minimal cost and minimal loss of information is detailed in this dissertation. The loss of information is directly related to the loss of accuracy of the coupled structure to represent video contents. During the same process of computing shot representations, the boundaries between shots are detected using the same modeling of contents and similarity measures.
When color and motion features are combined, the CMC representation provides an intermediate-level semantic descriptor that implicitly contains information about objects (their identities, sizes and motion patterns), camera operation, location, type of shot, temporal relationships between elements of the scene and global activity understood as the amount of action. More complex semantic concepts emerge from the combination of these intermediate-level descriptors, such as a "talking head" that combines a close-up with the skin color of a face. Adding the location component in the News domain, talking heads can be further classified into "anchors" (located in the studio) and "correspondents" (located outdoors). These and many other semantically meaningful categories are discovered when shots represented using the CMC model are clustered in an unsupervised way. Well-defined concepts are given by compact clusters, which can be determined by a measure of their density. High-level domain knowledge can then be defined by simple rules on these salient concepts, which will establish boundaries in the semantic structure of the video. The CMC modeling of video shots unifies the first steps of the video analysis process providing an intermediate-level semantically meaningful representation of contents without prior shot boundary detection.

This Master Thesis report was written by Umeå University Engineering Physics student Richard Tano during his thesis work at Ericsson Luleå. Monitoring network quality is of utmost importance to network providers. This can be done with models evaluating QoS (Quality of Service) and conforming to ITU-T Recommendations. When determining video stream quality there is of more importance to evaluatethe QoE (Quality of Experience) to understand how the user perceives the quality. This isranked in MOS (Mean opinion scores) values. An important aspect of determining the QoEis the video content type, which is correlated to the coding complexity and MOS values ofthe video. In this work the possibilities to improve quality estimation models complying to ITU-T study group 12 (q.14) was investigated. Methods were evaluated and an algorithm was developed that applies time series analysis of packet statistics for determination of videostreams MOS scores. Methods used in the algorithm includes a novel assembling of frequentpattern analysis and regression analysis. A model which incorporates the algorithm for usage from low to high bitrates was dened. The new model resulted in around 20% improvedprecision in MOS score estimation compared to the existing reference model. Furthermore an algorithm using only regression statistics and modeling of related statistical parameters was developed. Improvements in coding estimation was comparable with earlier algorithm but efficiency increased considerably.
Detta examensarbete skrevs av Richard Tano student på Umeå universitet åt Ericsson Luleå. Övervakning av nätets prestanda är av yttersta vikt för nätverksleverantörer. Detta görs med modeller för att utvärdera QoS (Quality of Service) som överensstämmer med ITU-T rekommendationer. Vid bestämning av kvaliten på videoströmmar är det mer meningsfullt att utvärdera QoE (Quality of Experience) för att få insikt i hur användaren uppfattar kvaliten. Detta graderas i värden av MOS (Mean opinion score). En viktig aspekt för att bestämma QoE är typen av videoinnehåll, vilket är korrelerat till videons kodningskomplexitet och MOS värden. I detta arbete undersöktes möjligheterna att förbättra kvalitetsuppskattningsmodellerna under uppfyllande av ITU-T studygroup 12 (q.14). Metoder undersöktes och en algoritm utvecklades som använder tidsserieanalys av paketstatistik för uppskattning av videoströmmars MOS-värden. Metoder som ingår i algoritmen är en nyutvecklad frekventa mönster metod tillsammans med regressions analys. En modell som använder algoritmen från låg till hög bithastighet definierades. Den nya modellen gav omkring 20% förbättrad precision i uppskattning av MOS-värden jämfört med existerande referensmodell. Även en algoritm som enbart använder regressionsstatistik och modellerande av statistiska parametrar utvecklades. Denna algoritm levererade jämförbara resultat med föregående algoritm men gav även kraftigt förbättrad effektivitet.

L'objectif de cette thèse est de proposer une solution au problème de la constance des couleurs entre les images d'une même scène acquises selon un même point de vue ou selon différents points de vue. Ce problème constitue un défi majeur en vision par ordinateur car d'un point de vue à l'autre, on peut être confronté à des variations des conditions d'éclairage (spectre de l'éclairage, intensité de l'éclairage) et des conditions de prise de vue (point de vue, type de caméra, paramètres d'acquisition tels que focus, exposition, balance des blancs, etc.). Ces variations induisent alors des différences d'apparence couleur entre les images acquises qui touchent soit sur l'ensemble de la scène observée soit sur une partie de celle-ci. Dans cette thèse, nous proposons une solution à ce problème qui permet de modéliser puis de compenser, de corriger, ces variations de couleur à partir d'une méthode basée sur quatre étapes : (1) calcul des correspondances géométriques à partir de points d'intérêt (SIFT et MESR) ; (2) calculs des correspondances couleurs à partir d'une approche locale; (3) modélisation de ces correspondances par une méthode de type RANSAC; (4) compensation des différences de couleur par une méthode polynomiale à partir de chacun des canaux couleur, puis par une méthode d'approximation linéaire conjuguée à une méthode d'estimation de l'illuminant de type CAT afin de tenir compte des intercorrélations entre canaux couleur et des changements couleur dus à l'illuminant. Cette solution est comparée aux autres approches de l'état de l'art. Afin d'évaluer quantitativement et qualitativement la pertinence, la performance et la robustesse de cette solution, nous proposons deux jeux d'images spécialement conçus à cet effet. Les résultats de différentes expérimentations que nous avons menées prouvent que la solution que nous proposons est plus performante que toutes les autres solutions proposées jusqu'alors
The objective of this thesis is to propose a solution to the problem of color consistency between images originate from the same scene irrespective of acquisition conditions. Therefore, we present a new color mapping framework that is able to compensate color differences and achieve color consistency between views of the same scene. Our proposed, new framework works in two phases. In the first phase, we propose a new method that can robustly collect color correspondences from the neighborhood of sparse feature correspondences, despite the low accuracy of feature correspondences. In the second phase, from these color correspondences, we introduce a new, two-step, robust estimation of the color mapping model: first, nonlinear channel-wise estimation; second, linear cross-channel estimation. For experimental assessment, we propose two new image datasets: one with ground truth for quantitative assessment; another, without the ground truth for qualitative assessment. We have demonstrated a series of experiments in order to investigate the robustness of our proposed framework as well as its comparison with the state of the art. We have also provided brief overview, sample results, and future perspectives of various applications of color mapping. In experimental results, we have demonstrated that, unlike many methods of the state of the art, our proposed color mapping is robust to changes of: illumination spectrum, illumination intensity, imaging devices (sensor, optic), imaging device settings (exposure, white balance), viewing conditions (viewing angle, viewing distance)

This bachelor thesis details the study and analysis of hopelessness, motivation, and personality types concerning game design. It offers definitions for hopelessness based on previous studies and explains what makes people experience hopelessness in games. The thesis compares previously conducted studies on hopelessness and motivation, confirms their validity, and applies the conclusion to theories of game design, such as MDA.

Video game advertising is a major venue for game industry to promote its products. As a form of advertising, game advertising reflects national cultural values. It also manifests game cultural values which gamers are able to identify with. Millions of people, youth and children in particular, are being exposed to game advertising. Video game advertising may not only influence viewers' purchasing decisions, but has the potential to influence their attitudes and perceptions of important societal issues such as gender roles, violence and sex. However, few studies have examined the information content and messages of game advertising. The purpose of this study is to begin to fill the gap. This study examined the content of 1,021 print game advertisements in four popular game magazines published between December 2006 and May 2008 in China and the United States. The study was built on a variety of theoretical backgrounds and game studies. First, built on Resnik and Stern's (1977) classification of information cues and conceptual differences between advertising service and tangible products, the study found that Chinese game advertisements used more information cues than U.S game advertisements. Second, built on a variety of cross-cultural frameworks including Hofstede's ─ individualism vs. collectivism, Kluckhohn and Strodtbeck's human and nature relationship and time orientation, the study found that that U.S. game advertisements used more individualistic appeals, manipulation-of-nature appeals and future-time-orientation appeals than Chinese game advertisements. It was found that Chinese game advertisements used more collectivistic appeals, oneness-with-nature appeals and past-time-orientation appeals than U.S. game advertisements. Third, the study, on the basis of synthesizing game literature, examined gender representation, sex and violence, and major game cultural values in Chinese and U.S. game ads. The study found that in both Chinese and U.S game advertisements, males were more likely to be featured (83.5% in U.S. ads and 55.9% in Chinese ads) as primary characters than females (12.4% in U.S. ads and 42% in Chinese ads). Female characters were sexualized when presented. The study also found 29.8% of Chinese advertisements contained sexual content and only 4% of U.S. game advertisements contained sexual content. It was found violent content was common in U.S. game advertisements and 61% of U.S. game advertisements contained violent content. U.S. game advertisements contained more violent words than Chinese game advertisements. The study examined three online game cultural characteristics reflected in game ads. Compared with U.S. ads, Chinese game advertisements used more character progression, virtual item accumulation and socialization appeals. Limitations of the study and directions for future study are discussed.

The problems of achieving high detection rate with low false alarm rate for human detection and tracking in video sequence, performance scalability, and improving response time are addressed in this thesis. The underlying causes are the effect of scene complexity, human-to-human interactions, scale changes, and scene background-human interactions. A two-stage processing solution, namely, human detection, and human tracking with two novel pattern classifiers is presented. Scale independent human detection is achieved by processing in the wavelet domain using square wavelet features. These features used to characterise human silhouettes at different scales are similar to rectangular features used in [Viola 2001]. At the detection stage two detectors are combined to improve detection rate. The first detector is based on shape-outline of humans extracted from the scene using a reduced complexity outline extraction algorithm. A Shape mismatch measure is used to differentiate between the human and the background class. The second detector uses rectangular features as primitives for silhouette description in the wavelet domain. The marginal distribution of features collocated at a particular position on a candidate human (a patch of the image) is used to describe statistically the silhouette. Two similarity measures are computed between a candidate human and the model histograms of human and non human classes. The similarity measure is used to discriminate between the human and the non human class. At the tracking stage, a tracker based on joint probabilistic data association filter (JPDAF) for data association, and motion correspondence is presented. Track clustering is used to reduce hypothesis enumeration complexity. Towards improving response time with increase in frame dimension, scene complexity, and number of channels; a scalable algorithmic architecture and operating accuracy prediction technique is presented. A scheduling strategy for improving the response time and throughput by parallel processing is also presented.

User Generated Content (UGC) has boosted a high popularity since the birth of a wide range of web services allowing the distribution of such user-produced media content, whose patterns vary from textual information, photo galleries to videos on site. The boom of Internet of Things and the newly released HTML5 accelerate the development of multimedia patterns as well as the technology of distributing it. YouTube, as one of the most popular video sharing site, enjoys the top most numbers of video views and video uploads per day in the world. With the rapid growing of multimedia patterns as well as huge bandwidth demand from subscribers, the sheer volume of the traffic is going to severely strain the network resources.</p><p>Therefore, analyzing media streaming traffic patterns and cacheability in live IP-access networks today leads a hot issue among network operators and content providers. One possible solution could be caching popular contents with a high replay rate in a proxy server on LAN border or in users' terminals.</p><p>Based on the solution, this thesis project focuses on developing a measurement framework to associate network cacheability with video category and video duration under a typical Swedish municipal network. Experiments of focused parameters are performed to investigate potential user behavior rules. From the analysis of the results, Music traffic gets a rather ideal network gain as well as a remarkable terminal gain, indicating that it is more efficient to be stored close to end user. Film&amp;Animation traffic, however, is preferable to be cached in the network due to its high net gain. Besides, it is optimal to cache the video clips with a length between 3 and 5 minutes, especially the Music and Film&amp;Animation traffic. In addition, more than half of the replays occur during 16.00-24.00 and peak hours appear on average from 18.00 to 22.00. Lastly, only around 16% of the videos are global popular and very few heavy users tend to be local popular video viewers, depicting local limits and independent user interests

Due to immense popularity of video games the author investigates the presence of gender portrayal within them. The purpose of this study is to thoroughly analyse a general phenomenon, such as gender, within video games to develop a better understanding of its particularities in this form of media and to expand the general body of knowledge on video games as a research topic. As prior literature shows, gender within video games can be either defined by its biased and sexualized character or by a tendency towards equality and strength for woman. To explain those varied results the author introduces the category of role as an important factor for character representation based on the use of theoretical frameworks of symbolic interactionism, more particularly dramaturgical approach of E. Goffman. She then further proceeds with a qualitative discourse analysis of both protagonist and support characters from 22 different games. The author finds that there is a visible difference within the manners females are presented depending on their role. Lead characters are more likely to be strong, independent and self-sufficient whereas support characters most often require immediate help, are dependent on others and are more likely to be abused. Presented results can account for some of the variety in prior research and they open the field of video game studies to possibly new research topics.

The purpose of this master thesis was to study different content-aware video retargeting techniques, concentrating on a generalization of seam carving for video. Focus have also been put on the possibility to combine different techniques to achieve better retargeting of both multi-shot video and single-shot video. This also involved significant studies of automatic cut detection and different measures of video content. The work resulted in a prototype application for semi-automatic video retargeting, developed in Matlab. Three different retargeting techniques, seam carving, automated pan & scan and subsampling using bi-cubic interpolation, have been implemented in the prototype. The techniques have been evaluated and compared to each other from a content preservation perspective and a perceived quality perspective.

Syftet med examensarbetet har varit att studera tekniker för ändring av bredd/höjd-förhållandet i videosekvenser, där hänsyn tas till innehållet i bilderna. Fokus har lagts på en generalisering av "seam carving" för video och möjligheterna att kombinera olika tekniker för att nå bättre kvalitet både för videosekvenser som består av endast ett, eller flera, klipp. Detta innefattade således också omfattande studier av automatisk klippdetektering och olika mått av videoinnehåll. Arbetet har resulterat i en prototypapplikation utvecklad i Matlab för halvautomatisk förändring av bildförhållande där hänsyn tas till innehållet i sekvenserna. I prototypen finns tre metoder implementerade, "seam carving", automatiserad "pan & scan" och nedsampling med bi-kubisk interpolering. Dessa metoder har utvärderats och jämförts med varandra från ett innehållsbevarande perspektiv och ett kvalitetsperspektiv.

Significant portion of today’s internet traffic emerge from multimedia services. When coupled with growth in number of users accessing these services, there is tremendous increase in network traffic. CDNs aid in handling this traffic and offer reliable services by distributing content across different locations. The concept of virtualization transformed traditional data centers into flexible cloud infrastructure. With the advent of cloud computing technology, multimedia providers have scope for establishing CDN using network operator’s cloud environment. However, the main challenge while establishing such CDN is implementing a cost efficient and dynamic mechanism which guarantees good service quality to users. This thesis aims to develop, implement and assess the performance of a model that coordinates deployment of virtual servers in the cloud. A solution which dynamically spawns and releases virtual servers according to variations in user demand has been proposed. Cost-based heuristic algorithm is presented for deciding the placement of virtual servers in OpenStack based federated clouds. Further, the proposed model is implemented on XIFI cloud and its performance is measured. Results of the performance study indicate that virtual CDNs offer reliable and prompt services. With virtual CDNs, multimedia providers can regulate expenses and have greater level of flexibility for customizing the virtual servers deployed at different locations.

The beauty community on YouTube is a popular outlet for influencer generated video content. Beauty YouTubers provide their viewers with makeup-related videos from tutorials to the latest trends on the platform. As a result, the influencers have gained high subscriber counts that generate revenue through advertisements and brand partnerships. The influencers create relationships with their subscribers that lead to loyalty in the form of video views and merchandise purchasing. This study provides a content analysis of common characteristics within 10 popular beauty YouTubers’ videos examining the strategies used by the influencers. The top five videos from each beauty YouTuber were selected resulting in a total of 50 videos analyzed. Parasocial Interaction and Framing theories were the theoretical frameworks for this study. The results of this study indicated a series of commonly used characteristics within the most popular videos posted by the top beauty influencers on YouTube.

VIDEO segmentation facilitates e±cient video indexing and navigation in large digital video archives. It is an important process in a content-based video indexing and retrieval (CBVIR) system. Many automated solutions performed seg- mentation by utilizing information about the \facts" of the video. These \facts" come in the form of labels that describe the objects which are captured by the cam- era. This type of solutions was able to achieve good and consistent results for some video genres such as news programs and informational presentations. The content format of this type of videos is generally quite standard, and automated solutions were designed to follow these format rules. For example in [1], the presence of news anchor persons was used as a cue to determine the start and end of a meaningful news segment. The same cannot be said for video genres such as movies and feature films. This is because makers of this type of videos utilized different filming techniques to design their videos in order to elicit certain affective response from their targeted audience. Humans usually perform manual video segmentation by trying to relate changes in time and locale to discontinuities in meaning [2]. As a result, viewers usually have doubts about the boundary locations of a meaningful video segment due to their different affective responses. This thesis presents an entirely new view to the problem of high level video segmentation. We developed a novel probabilistic method for affective level video content analysis and segmentation. Our method had two stages. In the first stage, a®ective content labels were assigned to video shots by means of a dynamic bayesian 0. Abstract 3 network (DBN). A novel hierarchical-coupled dynamic bayesian network (HCDBN) topology was proposed for this stage. The topology was based on the pleasure- arousal-dominance (P-A-D) model of a®ect representation [3]. In principle, this model can represent a large number of emotions. In the second stage, the visual, audio and a®ective information of the video was used to compute a statistical feature vector to represent the content of each shot. Affective level video segmentation was achieved by applying spectral clustering to the feature vectors. We evaluated the first stage of our proposal by comparing its emotion detec- tion ability with all the existing works which are related to the field of a®ective video content analysis. To evaluate the second stage, we used the time adaptive clustering (TAC) algorithm as our performance benchmark. The TAC algorithm was the best high level video segmentation method [2]. However, it is a very computationally intensive algorithm. To accelerate its computation speed, we developed a modified TAC (modTAC) algorithm which was designed to be mapped easily onto a field programmable gate array (FPGA) device. Both the TAC and modTAC algorithms were used as performance benchmarks for our proposed method. Since affective video content is a perceptual concept, the segmentation per- formance and human agreement rates were used as our evaluation criteria. To obtain our ground truth data and viewer agreement rates, a pilot panel study which was based on the work of Gross et al. [4] was conducted. Experiment results will show the feasibility of our proposed method. For the first stage of our proposal, our experiment results will show that an average improvement of as high as 38% was achieved over previous works. As for the second stage, an improvement of as high as 37% was achieved over the TAC algorithm.

Triggered by technology innovations, there has been a huge increase in the utilization of video, as one of the most preferred types of media due to its content richness, for many significant applications. To sustain an ongoing rapid growth of video information, there is an emerging demand for a sophisticated content-based video indexing system. However, current video indexing solutions are still immature and lack of any standard. One solution, namely annotation-based indexing, allows video retrieval using textual annotations. However, the major limitations are the restrictions of pre-defined keywords that can be used and the expensive manual work on annotating video. Another solution called feature-based indexing allows video search by low-level features comparison such as query by a sample image. Even though this approach can use automatically extracted features, users would not be able to retrieve video intuitively, based on high-level concepts. This predicament is caused by the so-called semantic gap which highlights the fact that users recall video contents in a high-level abstraction while video is generally stored as an arbitrary sequence of audio-visual tracks. To bridge the semantic gap, this thesis will demonstrate the use of domain-specific approach which aims to utilize domain knowledge in facilitating the extraction of high-level concepts directly from the audiovisual features. The main idea behind domain-specific approach is the use of domain knowledge to guide the integration of features from multi-modal tracks. For example, to extract goal segments from soccer and basketball video, slow motion replay scenes (visual) and excitement (audio) should be detected as they are played during most goal segments. Domain-specific indexing also exploits specific browsing and querying methods which are driven by specific users/applications’ requirements. Sports video is selected as the primary domain due to its content richness and popularity. Moreover, broadcasted sports videos generally span for hours with many redundant activities and the key segments could make up only 30% to 60% of the entire data depending on the progress of the match. This thesis presents a research work based on an integrated multi-modal approach for sports video indexing and retrieval. By combining specific features extractable from multiple (audio-visual) modalities, generic structure and specific events can be detected and classified. During browsing and retrieval, users will benefit from the integration of high-level semantic and some descriptive mid-level features such as whistle and close-up view of player(s). The main objective is to contribute to the three major components of sports video indexing systems. The first component is a set of powerful techniques to extract audio-visual features and semantic contents automatically. The main purposes are to reduce manual annotations and to summarize the lengthy contents into a compact, meaningful and more enjoyable presentation. The second component is an expressive and flexible indexing technique that supports gradual index construction. Indexing scheme is essential to determine the methods by which users can access a video database. The third and last component is a query language that can generate dynamic video summaries for smart browsing and support user-oriented retrievals.

The constantly increasing amount of video traffic is a challenge for service providers that need to maximize Quality of Experience (QoE) while optimizing the cost of their infrastructure. In this thesis, we address the problem of routing multiple HTTP-based Adaptive Streaming (HAS) sessions to maximize QoE. We first design a model linking the Quality of Service (QoS) Metrics to a single QoE score. This QoS-QoE model incorporates different QoE metrics and is able to learn online network variations and predict their impact on representative classes of adaptation logic, video motion and client resolution. Different QoE metrics are then combined into a QoE score based on ITU-T Rec. P.1202.2. This rich score is used to formulate the routing problem. We show that, even with a piece-wise linear QoE function in the objective, the routing problem without controlled rate allocation is non-linear. We therefore express a routing-plus-rate allocation problem and make it scalable with a dual subgradient approach based on Lagrangian relaxation where subproblems select a single path for each request with a trivial search, thereby connecting explicitly QoE, QoE and HAS bitrate. We show with ns-3 simulations that our algorithm provides values for HAS QoE metrics (quality, rebufferings, variation) equivalent to MILP and better than QoS-based approaches. Since ns-3 simulator cannot take in account different traffic queues for the same link we have then designed an emulated SDN solution based on a virtual switch with a virtual remote network controller and multiple lightweight clients to analyze the network behavior in the single bottleneck case.

La segmentation de vidéo en unités sémantiques temporelles fournit des indices qui sont importants pour organiser un parcours et une navigation efficaces basés sur le contenu. Dans ce travail nous sommes concernés avec le problème de macro-segmentation visant de produire automatiquement des tables des matières de vidéos. Nous proposons une méthode déterministe qui est une sorte d'un automate fini et qui permet de formuler des règles de segmentation basées sur la connaissance à priori des principes de production de vidéo. La méthode a été adoptée et évaluée sur la vidéo de tennis. Nous proposons aussi une approche statistique où les règles de segmention sont choisies de manière à ce que les indices de performance, précision et rappel, soient maximisés. L'approche est appliquée à la tâche de segmentation de films en scènes sémantiques. Dans ce travail nous sommes aussi concernés avec le problème de création automatique de résumé vidéo
Segmentation of video into temporal semantic units provides important indexing information for efficient content-based browsing and navigation. In this work we are concerned withe the problem of macro-segmentation aiming at automatic generating of content tables of videos. We propose a deterministic approach which is a sort of finite automation and allows one to formulate content parsing rules based on a priori knowledge of the video production principles. The approach has been adopted und tested on tennis video. We propose also a statistical segmentation framework where content parsing rules are chosen so as to optimize the system performance measured as recall and precision. The framework is applied to the task of film segmentation into semantic scenes. The higher segmentation performance has been shown with respect to conventional rule-based ans statistical methods. In this work we are also concerned with the problem of automatic video summarization

Contemporary research on media violence has shown the importance of examining the violent presentation of American video games and the correlation between games and the current U.S. game rating system. However, not many studies in this field have been conducted in China, especially regarding the importance of its pending official game rating system which has caused much controversy nationwide. In an effort to seek academic evidence for developing China's official game rating system, this study examined and compared the violence in fourteen of the most popular American and Chinese electronic games in 2004.These fourteen Chinese games and American games were selected for content analysis of the quantity and context of game violent interactions. The percentage breakdown of PATs (violent interactions) was coded by rate per minute, as was perpetrator characteristic, target characteristic, weapon used and visual perspective.The goal of the study was to determine if the popular Chinese electronic games carry as much violence as do popular American games, and if the context of violence in the former is significantly different from that in the latter. The American games were used as a basis for comparison to Chinese games for this study.The results of the study showed that popular Chinese games featured as much violence as American games. However, their context of violence was significantly different in terms of perpetrator characteristic, weapon used and visual perspective.Based on the results, the researcher concluded that China would definitely need a game rating system. However, the significant difference in the context of violence suggested that the Chinese rating system does not necessarily have to be the same as the U.S. system.
Department of Telecommunications

Stereotypes and threatening images are present in much of our modern entertainment media often going unnoticed for the effects they may have on society. One media which is relatively new and unexplored when it comes to these stereotypes and images of threat is the video game media. This thesis explores how stereotypes are created and maintained within video games and how securitization efforts affect entertainment media, in order to pursue these aims the game Call of Duty: Modern Warfare (2019) is analysed with a content analysis built on the theories of othering and securitization, in order to see how the Russians are portrayed within the game. The analysis shows that the image attached to Russians is overly negative compared to other people in the game, and the common threats which they pose is going to war with the West. Based on these findings, the thesis concludes that video games do reproduce securitization discourses and create stereotypes.

This study examines the infotainment versus social responsibility debate as it applies to local television newscasts in the United States. An overview of the concerns surrounding infotainment as news follows, including a look at a newsroom's traditional responsibilities to its viewers, as well as its current role in adding to parent company profit. Socially responsible hard news and infotainment characteristics are defined as they apply to television news broadcasts, both within the context of news story content and in presentation style. A descriptive content analysis examines these characteristics within the late night local newscasts airing in Portland, Oregon. Portland is a large broadcast news market with over one million potential local news viewers. It is also a community with an exceptionally high rate of civic engagement (Abbott, 2001; Putnam & Feldstein, 2003). Its media coverage of the city, however, has been the subject of criticism by local columnists and national journalism scholars. A socially responsible news product would provide the city's residents with the information needed to continue the trend of participation, community betterment, and overall citizenship knowledge.

Aim:  The overall aim of this thesis was to explore the development of a video-supported interactive learning model for movement awareness among nursing students. Methods:  Study I was a cross-sectional survey regarding prevalence and impact of musculoskeletal symptoms (MSS) among nursing students. In the remaining three studies a learning model was developed and explored; II - the inter-personal interaction (qualitative content analysis), III - the students’ experiences of using the learning model (phenomenological hermeneutics), IV - the students’ learning processes (hermeneutic approach). Results: 143 of the 224 respondents in study I reported MSS during the previous 12 months and of those 91 reported impact on physical daily life activities. The odds ratio for reporting MSS study year 3 was 4.7 (95% CI: 2.1 – 10.7). Study II shows that the students’ movement awareness and self-analysis developed when encountering their own movement through video feedback. Studies III and IV show that the facilitator’s reflective and responsive approach appears to be essential in creating interaction and a permitting learning atmosphere. The students became emotionally and cognitively challenged and personally engaged, were motivated to change by discovering details in their movements and gained a greater understanding of the relationship between their own movements and current or risk for future MSS. They also experienced emotional, cognitive and bodily confusion, which was interpreted as a necessary step in the changing process. Conclusion: MSS among nursing students appears to be a problem and education regarding ergonomic movements and principles is suggested to be emphasized in the nursing curriculum. The video-supported learning model enabled encountering and discovering one’s own body and movement in different ways, which facilitated reflection and motivation for change, which was supported by the facilitator’s reflective approach. The learning model, which could contribute to multifactorial ergonomic interventions, could also support movement awareness and learning in practical learning situations within education and rehabilitation. Further research needs to study the model in different contexts and in relation to MSS prevention.

Analyzing 195 televised political ads from the United States and Canada in 2004 and 2008, this research studies the use of issue and image ads and the attack, acclaim, and contrast function of ads in presidential and federal elections. Results indicate that there is no statistical difference in the use of issue or image ads and no statistical difference in the function of ads in both nations in 2004 and 2008. Issue ads are found to be more commonly used in Canada than in the United States, but there is no statistical difference in the use of acclaim ads between the United States and Canada. Winners in both nations are found to use issue ads more than image ads while winners in Canadian elections were found to use issue ads more than winners of American elections. This study also offers a methodological finding regarding the analysis of issue or image in political advertising. Limitations and implications for future research are also discussed.

This study explores the representation of nerds and geeks in popular broadcast television programs over the course of the past twenty years. A content analysis of the five most popular scripted broadcast television programs for each year was conducted in order to assess the frequency of nerd characters, as well as the social competence, physical attractiveness, and demographic information of each such character. In addition, a supplemental survey design study was employed in order to collect public opinion data regarding perceptions of nerds in general and on television. The results of these studies indicated that while the per-year frequency of nerd portrayals has not varied significantly, nerds have been consistently portrayed as overwhelmingly white and male. Nerd characters in popular television programs have grown more physically attractive over the past twenty years. Furthermore, while technological or computer-related expertise remain significant predictors for the identification of television characters as nerds by audience members, the same is true for unattractiveness and low social competence. Considered through the theoretical framework provided by past mass media scholars, these findings suggest that nerds represent a group of individuals consistently portrayed as possessing technical aptitudes which are highly desirable in the current social context, but that such roles are portrayed as accessible only to white males.

Les documents visuels comprenant des images et des vidéos sont en croissance rapide sur Internet et dans nos collections personnelles. Cela nécessite une analyse automatique du contenu visuel qui fait appel à la conception de méthodes intelligentes pour correctement indexer, rechercher et récupérer des images et des vidéos. Cette thèse vise à améliorer la détection automatique des concepts dans les vidéos sur Internet. Nos contributions portent sur des différents niveaux dans le cadre de détection de concept et peuvent être divisés en trois parties principales. La première partie se focalise sur l’amélioration du modèle de représentation des vidéos « Bag-of-Words (BOW) » en proposant un nouveau mécanisme de construction qui utilise des étiquettes de concepts et une autre technique qui ajoute un raffinement à la signature BOW basée sur la distribution de ses éléments. Nous élaborons ensuite des méthodes pour intégrer des entités semblables et dissemblables pour construire des modèles de reconnaissance améliorés dans la deuxième partie. A ce stade-là, nous observons l’information potentielle que les concepts partagent et construisons des modèles pour les méta-concepts dont sont dérivés les résultats spécifiques de concepts. Cela améliore la reconnaissance des concepts qui ont peu d’exemples annotés. Enfin, nous concevons certaines méthodes d'apprentissage semi-supervisé pour bénéficier de la quantité importante de données non étiquetées. Nous proposons des techniques pour améliorer l'algorithme de cotraining avec une sélection optimale des classifieurs utilisés
Visual material comprising images and videos is growing ever so rapidly over the internet and in our personal collections. This necessitates automatic understanding of the visual content which calls for the conception of intelligent methods to correctly index, search and retrieve images and videos. This thesis aims at improving the automatic detection of concepts in the internet videos by exploring all the available information and putting the most beneficial out of it to good use. Our contributions address various levels of the concept detection framework and can be divided into three main parts. The first part improves the Bag of Words (BOW) video representation model by proposing a novel BOW construction mechanism using concept labels and by including a refinement to the BOW signature based on the distribution of its elements. We then devise methods to incorporate knowledge from similar and dissimilar entities to build improved recognition models in the second part. Here we look at the potential information that the concepts share and build models for meta-concepts from which concept specific results are derived. This improves recognition for concepts lacking labeled examples. Lastly we contrive certain semi-supervised learning methods to get the best of the substantial amount of unlabeled data. We propose techniques to improve the semi-supervised cotraining algorithm with optimal view selection

The aim of this thesis is to determine how the debate about equality in the culture of video and computer games appears in different kind of web based media. And what underlying reasons may affect the outcome of the discourse. The theoretical perspectives used in this study is based on a gender perspective complemented with the concept of hegemony, myths and stereotypes. This examination is based on a critical discourse analysis and Fairclough’s three dimensional model of discourse, the material has been collected with a quantitative content analysis. The result of the study shows that inequality in the culture of video and computer games is a big problem. The result is a study of constant repression against women, threats and harassment. The deduction of this study is that the patriarchy is the fundamental structure that has created the current culture of gaming. And as long as the patriarchy exsists, so will the inequality, not only in society, but in the ever growing culture of video and computer games.

The following study investigates how recent games (2014 - 2018) visualize health and health changes, with a focus on the player character’s health, the player character taking damage and the graphical user interface (GUI). 50 games were coded via gameplay videos on YouTube and then analysed. The codes were then grouped together based on patterns and theoretical grounding. These groups were then examined with other studies and game design practices.
Följande studie ämnar att undersöka hur spel från senaste tiden (2014 - 2018) visualiserar hälsa och hälsoförändringar, med ett fokus på spelarkaraktärens hälsa, när spelarkaraktären tar skada och GUI. 50 spel kodades via s.k. “gameplay” videor på YouTube och har sedan blivit analyserade. Koderna var sedan grupperade baserad på mönster och teori. Dessa grupper var sedan undersökta med andra studier och speldesign sedvänjor.

This study examines how costume design is used as a narrative and functional part of video game character design. The purpose being how costume design is currently utilized, what common design trends can be found and in which instances costume design goes against the functionality and believability of the character. One character from each top selling single player third person game between the years 2015-2018 were chosen for the sample. A character analysis and a coding scheme were created to find common design trends used to visually display information to players. The results showed a prevalent use of real-world cues and signs to visually display instant information. Contradicting real-world cues used together can show a divergence from reality, but even with a lack of real world examples a uniform design language can be seen. The results also show the use of objects with contextual meaning being an important part of costume design, giving it more depth. The instances found of contradicting costume design were predominantly used to make the character stand out or to emphasize their attractiveness.
Denna studie undersöker hur kostymdesign används som en narrativ och funktionell del inom design av spelkaraktärer. Syftet är att se hur kostymdesign nuvarande används, vilka vanliga design trender som kan hittas och vilka instanser som finns där kostymdesign går emot trovärdighet och funktionalitet. En karaktär från varje toppsäljande spel med enspelarläge och tredjepersons perspektiv mellan år 2015-2018 valdes. En karaktärsanalys och ett kodschema skapades för att hitta gemensamma design trender som används för att visuellt förmedla information till spelare. Resultatet visar en övergripande användning av signaler från verkligheten för att visuellt förmedla omedelbar information. Motsägande verkliga signaler som visas tillsammans kan påvisa en avvikelse från verkligheten men även scenarion med en avsaknad av verkliga exempel kan ett uniformt designspråk ses. Resultaten visade även den vikt som läggs på användningen av objekt med kontextuell mening för att ge kostymdesigner mer djup. Instanser där kostymdesign sågs som motsägande var mestadels för att få karaktären att stå ut eller för att framhäva attraktiva drag.

This research examines Subscription Video On-Demand (SVOD) using Netflix as one of the main examples that has seen a dramatic increase in usage in recent years compared to the traditional way of viewing content through television. Using focus group sessions and an online survey, a qualitative analysis approach is used by way of a thematic analysis to elaborate and gain insight into the phenomenon of SVOD within our society which has allowed viewers to alter time shifting and self-scheduling habits. Watching online film and television over the internet, forces the breakdown of the traditional value chain of viewing methods as well as consumption of it. This research aims to narrow this research gap surrounding SVOD. The results will be used to add value to the research area of this growing and changing phenomenon of online TV consumption with SVOD.
Aquesta recerca estudia el vídeo a la carta de pagament (SVOD, en anglès) a partir de l'exemple de Netflix, el qual ha vist un increment considerable de consum al llarg dels últims anys, especialment comparat amb els mitjans de comunicació tradicionals. A través de focus group i una enquesta en línia, es fa una anàlisi qualitativa que parteix d'un estudi temàtic, a fi d'elaborar i obtenir una idea del fenomen de l'SVOD dintre de la nostra societat. Aquest fenomen ha permès als espectadors alterar els hàbits d'horari d'ús i d'autoprogramació. Veure pel·licules i televisió a través d'internet força a trencar la cadena tradicional de valor dels mètodes de visionat així com el consum dels mateixos.

Im Vergleich zu einer stichwortbasierten Suche ermöglicht die semantische Suche ein präziseres und anspruchsvolleres Durchsuchen von (Web)-Dokumenten, weil durch die explizite Semantik Mehrdeutigkeiten von natürlicher Sprache vermieden und semantische Beziehungen in das Suchergebnis einbezogen werden können. Eine semantische, Entitäten-basierte Suche geht von einer Anfrage mit festgelegter Bedeutung aus und liefert nur Dokumente, die mit dieser Entität annotiert sind als Suchergebnis. Die wichtigste Voraussetzung für eine Entitäten-zentrierte Suche stellt die Annotation der Dokumente im Archiv mit Entitäten und Kategorien dar. Textuelle Informationen werden analysiert und mit den entsprechenden Entitäten und Kategorien versehen, um den Inhalt semantisch erschließen zu können. Eine manuelle Annotation erfordert Domänenwissen und ist sehr zeitaufwendig. Die semantische Annotation von Videodokumenten erfordert besondere Aufmerksamkeit, da inhaltsbasierte Metadaten von Videos aus verschiedenen Quellen stammen, verschiedene Eigenschaften und Zuverlässigkeiten besitzen und daher nicht wie Fließtext behandelt werden können. Die vorliegende Arbeit stellt einen semantischen Analyseprozess für Video-Metadaten vor. Die Eigenschaften der verschiedenen Metadatentypen werden analysiert und ein Konfidenzwert ermittelt. Dieser Wert spiegelt die Korrektheit und die wahrscheinliche Mehrdeutigkeit eines Metadatums wieder. Beginnend mit dem Metadatum mit dem höchsten Konfidenzwert wird der Analyseprozess innerhalb eines Kontexts in absteigender Reihenfolge des Konfidenzwerts durchgeführt. Die bereits analysierten Metadaten dienen als Referenzpunkt für die weiteren Analysen. So kann eine möglichst korrekte Analyse der heterogen strukturierten Daten eines Kontexts sichergestellt werden. Am Ende der Analyse eines Metadatums wird die für den Kontext relevanteste Entität aus einer Liste von Kandidaten identifiziert - das Metadatum wird disambiguiert. Hierfür wurden verschiedene Disambiguierungsalgorithmen entwickelt, die Beschreibungstexte und semantische Beziehungen der Entitätenkandidaten zum gegebenen Kontext in Betracht ziehen. Der Kontext für die Disambiguierung wird für jedes Metadatum anhand der Eigenschaften und Konfidenzwerte zusammengestellt. Der vorgestellte Analyseprozess ist an zwei Hypothesen angelehnt: Um die Analyseergebnisse verbessern zu können, sollten die Metadaten eines Kontexts in absteigender Reihenfolge ihres Konfidenzwertes verarbeitet werden und die Kontextgrenzen von Videometadaten sollten durch Segmentgrenzen definiert werden, um möglichst Kontexte mit kohärentem Inhalt zu erhalten. Durch ausführliche Evaluationen konnten die gestellten Hypothesen bestätigt werden. Der Analyseprozess wurden gegen mehrere State-of-the-Art Methoden verglichen und erzielt verbesserte Ergebnisse in Bezug auf Recall und Precision, besonders für Metadaten, die aus weniger zuverlässigen Quellen stammen. Der Analyseprozess ist Teil eines Videoanalyse-Frameworks und wurde bereits erfolgreich in verschiedenen Projekten eingesetzt.
The Semantic Web provides information contained in the World Wide Web as machine-readable facts. In comparison to a keyword-based inquiry, semantic search enables a more sophisticated exploration of web documents. By clarifying the meaning behind entities, search results are more precise and the semantics simultaneously enable an exploration of semantic relationships. However, unlike keyword searches, a semantic entity-focused search requires that web documents are annotated with semantic representations of common words and named entities. Manual semantic annotation of (web) documents is time-consuming; in response, automatic annotation services have emerged in recent years. These annotation services take continuous text as input, detect important key terms and named entities and annotate them with semantic entities contained in widely used semantic knowledge bases, such as Freebase or DBpedia. Metadata of video documents require special attention. Semantic analysis approaches for continuous text cannot be applied, because information of a context in video documents originates from multiple sources possessing different reliabilities and characteristics. This thesis presents a semantic analysis approach consisting of a context model and a disambiguation algorithm for video metadata. The context model takes into account the characteristics of video metadata and derives a confidence value for each metadata item. The confidence value represents the level of correctness and ambiguity of the textual information of the metadata item. The lower the ambiguity and the higher the prospective correctness, the higher the confidence value. The metadata items derived from the video metadata are analyzed in a specific order from high to low confidence level. Previously analyzed metadata are used as reference points in the context for subsequent disambiguation. The contextually most relevant entity is identified by means of descriptive texts and semantic relationships to the context. The context is created dynamically for each metadata item, taking into account the confidence value and other characteristics. The proposed semantic analysis follows two hypotheses: metadata items of a context should be processed in descendent order of their confidence value, and the metadata that pertains to a context should be limited by content-based segmentation boundaries. The evaluation results support the proposed hypotheses and show increased recall and precision for annotated entities, especially for metadata that originates from sources with low reliability. The algorithms have been evaluated against several state-of-the-art annotation approaches. The presented semantic analysis process is integrated into a video analysis framework and has been successfully applied in several projects for the purpose of semantic video exploration of videos.

This study has been performed to give light to numerous observations from earlier studies in how characters are represented in video games. Through examination of 884 characters from 60 games and comparing them to each other depending if the game was violent or not, was a fighting game or not and how popular the game was this study was looking to find several answers regarding how the game industry works and how characters are being represented depending on these factors. This study found that the gender distribution has partially levelled out since former studies (Williams, et al., 2009; Downs och Smith, 2010) and that the hypersexualized  representation has decreased for female characters but increased for male characters for some hypersexual variables. Violent and fighting games hade larger male distribution of male characters, but only fighting games had more hypersexualized characters than its counterpart. Analyses regarding how popular the games was in comparison to each other gave no concrete results.
Denna studie har utförts för att ge ljus till flertalet observationer från tidigare studier om hur karaktärer representeras i digitala spel. Genom att undersöka 884 karaktärer från 60 spel och jämföra dem mot varandra beroende på om spelen var våldsamma eller ej, om spelet var ett slagsmålsspel eller ej och hur populärt spelet var söktes det flera svar om spelbranschen och hur karaktärer representeras beroende på dessa faktorer. Studien fann att könsfördelningen hade utjämnats delvis sedan tidigare studier (Williams, m fl., 2009; Downs och Smith, 2010) och att hypersexualiserad representation hade sjunkit för kvinnliga karaktärer men höjts för manliga karaktärer för vissa hypersexualiserade bedömningar. Våldsamma och slagsmålsspel hade större andelar män, men endast slagsmålsspel hade fler hypersexualiserade karaktärer än sin motpart. Analyser som berodde på hur populära spelen var i jämförelse med varandra visade inget konkret.

This content analysis study of music videos answered questions concerning the amount and severity of violence content during different time periods of the day. A system of classifying violence content as nonviolent, mostly light, neither light nor serious, mostly serious, and extremely serious was used to evaluate music videos from MTV. One hour from each day was randomly selected for evaluation for a period of thirty days. During this time, there were 313 occurrences of music videos which were aired and subsequently evaluated. The results indicated the majority of these music videos contained mostly light or no violence content. This study also revealed that the most likely time of day a viewer would see videos with violence would be from midnight until eight in the morning.

Under pandemin COVID-19 har hälsovården tvingats till hastiga anpassningar i form av användning av vård via videolänk för kontinuitet, vilket berör även psykoterapi. Trots omfattande evidens för effektiviteten av terapi via videolänk finns fortfarande myter hos kliniker att den terapeutiska alliansen äventyras i det digitala forumet, vilket kan försvåra implementeringen. Studiens syfte var att utforska psykoterapeuters upplevelser av psykoterapi via videolänk, med särskilt fokus på den terapeutiska alliansen (TA). Genom semi-strukturerade intervjuer undersöktes psykoterapeuters föreställningar, anpassningar samt erfarenheter av denna omställning. Data analyserades utifrån kvalitativ innehållsanalys och resulterade i tre kategorier; Kommunikation, Den bärande relationen samt KBT-interventionerna. Huvudresultatet indikerar att klinikerna har behövt anpassa behandlingen kontextuellt, kommunikativt samt innehållsmässigt för att främja alliansen, och att TA går att utveckla över videolänk. Detta sammanfaller med tidigare internationella studiers resultat.  Utvecklingsområden som framkommit är aspekter självexponering som nytt fenomen och förändringar i maktstrukturen inom terapin. Omställningen har gått över förväntan positivt och delvis förändrat respondenternas inställning till videolänkterapi. Inom begränsningarna för denna studie beskrivs konsekvenserna och framtida forskningsriktningar.
During the pandemic COVID-19 the health care has suddenly been forced to adjust their work and start using video conference to keep the continuity, which also impacts psychotherapy. Despite extensive evidence of the efficiency of video conference psychotherapy there are still myths among clinicians that the therapeutic alliance can be endangered by the digital format, which can complicate the implementations. The aim of this study is to examine the psychotherapists' experiences of psychotherapy via video conference, with particular focus on the therapeutic alliance (TA). Through semi-structured interviews we examined the psychotherapists conceptions, adaptations and the experiences of this readjustment. Data were analyzed based on qualitative content analysis; Communication, The solid relation and the CBT-interventions. The main results indicated that the clinicians needed to adapt the treatment contextually, communicatively and in terms of content to frame TA, and that TA can be developed via video conference. This coincides with previous international research. Areas of development is the new phenomenon self-exposure and transformation/change of equalization of power.  The conversion has positively exceeded the expectations and has partly changed the respondents attitudes to therapy via video conference. Within the limitations of this study, implications and further directions for research are described.

De nos jours, l’expérience de l'utilisateur appelé en anglais « User Experience » est devenue l’un des indicateurs les plus pertinents pour les fournisseurs de services ainsi que pour les opérateurs de télécommunication pour analyser le fonctionnement de bout en bout de leurs systèmes (du terminal client, en passant par le réseaux jusqu’à l’infrastructure des services etc.). De plus, afin d’entretenir leur part de marché et rester compétitif, les différents opérateurs de télécommunication et les fournisseurs de services doivent constamment conserver et accroître le nombre de souscription des clients. Pour répondre à ces exigences, ils doivent disposer de solutions efficaces de monitoring et d’estimation de la qualité d'expérience (QoE) afin d’évaluer la satisfaction de leur clients. Cependant, la QoE est une mesure qui reste subjective et son évaluation est coûteuse et fastidieuse car elle nécessite une forte participation humaine (appelé panel de d’évaluation). Par conséquent, la conception d’un outil qui peut mesurer objectivement cette qualité d'expérience avec une précision raisonnable et en temps réel est devenue un besoin primordial qui constitue un challenge intéressant à résoudre. Comme une première contribution, nous avons analysé l'impact du comportement d’un réseau sur la qualité des services de vidéo à la demande (VOD). Nous avons également proposé un outil d'estimation objective de la QoE qui utilise le système expert basé sur la logique floue pour évaluer la QoE à partir des paramètres de qualité de service de la couche réseau. Dans une deuxième contribution, nous avons analysé l'impact des paramètres QoS de couche MAC sur les services de VoD dans le cadre des réseaux sans fil IEEE 802.11n. Nous avons également proposé un outil d'estimation objective de la QoE qui utilise le réseau aléatoire de neurones pour estimer la QoE dans la perspective de la couche MAC. Pour notre troisième contribution, nous avons analysé l'effet de différents scénarios d'adaptation sur la QoE dans le cadre du streaming adaptatif au débit. Nous avons également développé une plate-Forme Web de test subjectif qui peut être facilement intégré dans une plate-Forme de crowd-Sourcing pour effectuer des tests subjectifs. Finalement, pour notre quatrième contribution, nous avons analysé l'impact des différents paramètres de qualité de service Web sur leur QoE. Nous avons également proposé un algorithme d'apprentissage automatique i.e. un système expert hybride rugueux basé sur la logique floue pour estimer objectivement la QoE des Web services
Today user experience is becoming a reliable indicator for service providers and telecommunication operators to convey overall end to end system functioning. Moreover, to compete for a prominent market share, different network operators and service providers should retain and increase the customers’ subscription. To fulfil these requirements they require an efficient Quality of Experience (QoE) monitoring and estimation. However, QoE is a subjective metric and its evaluation is expensive and time consuming since it requires human participation. Therefore, there is a need for an objective tool that can measure the QoE objectively with reasonable accuracy in real-Time. As a first contribution, we analyzed the impact of network conditions on Video on Demand (VoD) services. We also proposed an objective QoE estimation tool that uses fuzzy expert system to estimate QoE from network layer QoS parameters. As a second contribution, we analyzed the impact of MAC layer QoS parameters on VoD services over IEEE 802.11n wireless networks. We also proposed an objective QoE estimation tool that uses random neural network to estimate QoE from the MAC layer perspective. As our third contribution, we analyzed the effect of different adaption scenarios on QoE of adaptive bit rate streaming. We also developed a web based subjective test platform that can be easily integrated in a crowdsourcing platform for performing subjective tests. As our fourth contribution, we analyzed the impact of different web QoS parameters on web service QoE. We also proposed a novel machine learning algorithm i.e. fuzzy rough hybrid expert system for estimating web service QoE objectively

Nous abordons le problème de la synchronisation automatique d'un contenu audiovisuel avec une procédure textuelle qui le décrit. La stratégie consiste à extraire des informations sur la structure des deux contenus puis à les mettre en correspondance. Nous proposons deux outils d'analyse vidéo qui extraient respectivement : * les limites des évènements d'intérêt à l'aide d'une méthode de quantification de type dictionnaire * les segments dans lesquels une action se répète en exploitant une méthode d'analyse fréquentielle : le YIN. Ensuite, nous proposons un système de synchronisation qui fusionne les informations fournies par ces outils pour établir des associations entre les instructions textuelles et les segments vidéo correspondants. Une "Matrice de confiance" est construite et exploitée de manière récursive pour établir ces associations en regard de leur fiabilité
We address the problem of automatic synchronization of an audiovisual content with a procedural text that describes it. The strategy consists in extracting pieces of information about the structure from both contents, and in matching them depending on their types. We propose two video analysis tools that respectively extract: * Limits of events of interest using an approach inspired by dictionary quantization. * Segments that enclose a repeated action based on the YIN frequency analysis method. We then propose a synchronization system that merges results coming from these tools in order to establish links between textual instructions and the corresponding video segments. To do so, a "Confidence Matrix" is built and recursively processed in order to identify these links in respect with their reliability