Увійти

Готові списки джерел за темами / Spatial-semantic model

Зміст

Статті в журналах
Дисертації
Книги
Частини книг
Тези доповідей конференцій
Звіти організацій

Добірка наукової літератури з теми "Spatial-semantic model"

Автор: Grafiati

Опубліковано: 30 травня 2022

Оновлено: 19 липня 2025

Оформте джерело за APA, MLA, Chicago, Harvard та іншими стилями

Оберіть тип джерела:

Ознайомтеся зі списками актуальних статей, книг, дисертацій, тез та інших наукових джерел на тему "Spatial-semantic model".

Біля кожної праці в переліку літератури доступна кнопка «Додати до бібліографії». Скористайтеся нею – і ми автоматично оформимо бібліографічне посилання на обрану працю в потрібному вам стилі цитування: APA, MLA, «Гарвард», «Чикаго», «Ванкувер» тощо.

Також ви можете завантажити повний текст наукової публікації у форматі «.pdf» та прочитати онлайн анотацію до роботи, якщо відповідні параметри наявні в метаданих.

Статті в журналах з теми "Spatial-semantic model"

1

Peng, Huilin, Yang Wang, and Hao Ge. "Spatial-Semantic Transformer for Spatial Relation Recognition." Journal of Physics: Conference Series 2583, no. 1 (2023): 012001. http://dx.doi.org/10.1088/1742-6596/2583/1/012001.

Повний текст джерела

Анотація:

Abstract Spatial relation recognition, which aims to predict a spatial relation predicate, has attracted increasing attention in the computer vision study. During tackling this problem, modeling spatial relation of the subjects and objects is of great importance. We find that only using spatial features leads to poor results in predicting the spatial relation. To overcome these challenges, we propose an effective spatial attention module to enhance spatial features using semantic features. After identifying the importance of spatial attention mechanism, we propose a spatial transformer module with encoder layers to recognize unseen spatial relation based on spatial attention mechanism. Extensive experiments on the benchmark dataset (SpatialSense) show that, by using refined spatial feature, our spatial transformer model and spatial attention model achieve state-of-the-art performance on overall accuracy.

Стилі APA, Harvard, Vancouver, ISO та ін.

2

Abburu, Sunitha. "Geospatial Semantic Query Engine for Urban Spatial Data Infrastructure." International Journal on Semantic Web and Information Systems 15, no. 4 (2019): 31–51. http://dx.doi.org/10.4018/ijswis.2019100103.

Повний текст джерела

Анотація:

The research aims at design and develop a special semantic query engine “CityGML Spatial Semantic Web Client (CSSWC)” that facilitates ontology-based multicriteria queries on CityGML data in OGC standard. Presently, there is no spatial method, spatial information infrastructure or any tool to establish the spatial semantic relationship between the 3D city objects in CityGML model. The present work establishes the spatial and semantic relationships between the 3DCityObjects and facilitates ontology-driven spatial semantic query engine on 3D city objects, class with multiple attributes, spatial semantic relations like crosses, nearby, etc., with all other city objects. This is a novel and original work practically implemented generic product for any 3D CityGML model on the globe. A user-friendly form-based interface is designed to compose effective ontology based GeoSPARQL query. CSSWC enhances CityGML applications performance through effective and efficient querying system.

Стилі APA, Harvard, Vancouver, ISO та ін.

3

Wu, Tao, Jianxin Qin, and Yiliang Wan. "TOST: A Topological Semantic Model for GPS Trajectories Inside Road Networks." ISPRS International Journal of Geo-Information 8, no. 9 (2019): 410. http://dx.doi.org/10.3390/ijgi8090410.

Повний текст джерела

Анотація:

To organize trajectory data is a challenging issue for both studies on spatial databases and spatial data mining in the last decade, especially where there is semantic information involved. The high-level semantic features of trajectory data exploit human movement interrelated with geographic context, which is becoming increasingly important in representing and analyzing actual information contained in movements and further processing. This paper argues for a novel semantic trajectory model named TOST. It considers both semantic and geographic information of trajectory data happens along network infrastructure simultaneously. In TOST, a flexible intersection-based semantic representation is designed to express movement typically constrained by urban road networks by combining sets of local semantic details along the time axis. A relational schema based on this model was instantiated against real datasets, which illustrated the effectivity of our proposed model.

Стилі APA, Harvard, Vancouver, ISO та ін.

4

Han, Dongfeng, Wenhui Li, and Zongcheng Li. "Semantic image classification using statistical local spatial relations model." Multimedia Tools and Applications 39, no. 2 (2008): 169–88. http://dx.doi.org/10.1007/s11042-008-0203-6.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

5

Mościcka, Albina. "Europeana Data Model in GIS for movable heritage." Geografie 120, no. 4 (2015): 527–41. http://dx.doi.org/10.37040/geografie2015120040527.

Повний текст джерела

Анотація:

The paper proposes to use European resources in GIS as a set of multi-spatial objects with semantic relations to the space. It improves the analysis and visualization of geographic or contextual associations between various items. This paper aims to integrate the Europeana Data Model with GIS for movable heritage based on semantic relations of movable objects with the space. All classes and properties of the EDM were analyzed. Classes and properties containing spatial information were examined and their semantic relations to the space were proposed. All aspects of the relations of movable heritage objects and space were taken into consideration, and examples of the GIS-based pilot resources saved with the use of EDM rules are proposed.

Стилі APA, Harvard, Vancouver, ISO та ін.

6

Jia, Chengyou, Minnan Luo, Zhuohang Dang, et al. "SSMG: Spatial-Semantic Map Guided Diffusion Model for Free-Form Layout-to-Image Generation." Proceedings of the AAAI Conference on Artificial Intelligence 38, no. 3 (2024): 2480–88. http://dx.doi.org/10.1609/aaai.v38i3.28024.

Повний текст джерела

Анотація:

Despite significant progress in Text-to-Image (T2I) generative models, even lengthy and complex text descriptions still struggle to convey detailed controls. In contrast, Layout-to-Image (L2I) generation, aiming to generate realistic and complex scene images from user-specified layouts, has risen to prominence. However, existing methods transform layout information into tokens or RGB images for conditional control in the generative process, leading to insufficient spatial and semantic controllability of individual instances. To address these limitations, we propose a novel Spatial-Semantic Map Guided (SSMG) diffusion model that adopts the feature map, derived from the layout, as guidance. Owing to rich spatial and semantic information encapsulated in well-designed feature maps, SSMG achieves superior generation quality with sufficient spatial and semantic controllability compared to previous works. Additionally, we propose the Relation-Sensitive Attention (RSA) and Location-Sensitive Attention (LSA) mechanisms. The former aims to model the relationships among multiple objects within scenes while the latter is designed to heighten the model's sensitivity to the spatial information embedded in the guidance. Extensive experiments demonstrate that SSMG achieves highly promising results, setting a new state-of-the-art across a range of metrics encompassing fidelity, diversity, and controllability.

Стилі APA, Harvard, Vancouver, ISO та ін.

7

Li, Wenchao, Xin Liu, Chenggang Yan, Guiguang Ding, Yaoqi Sun, and Jiyong Zhang. "STS: Spatial–Temporal–Semantic Personalized Location Recommendation." ISPRS International Journal of Geo-Information 9, no. 9 (2020): 538. http://dx.doi.org/10.3390/ijgi9090538.

Повний текст джерела

Анотація:

The rapidly growing location-based social network (LBSN) has become a promising platform for studying users’ mobility patterns. Many online applications can be built based on such studies, among which, recommending locations is of particular interest. Previous studies have shown the importance of spatial and temporal influences on location recommendation; however, most existing approaches build a universal spatial–temporal model for all users despite the fact that users always demonstrate heterogeneous check-in behavior patterns. In order to realize truly personalized location recommendations, we propose a Gaussian process based model for each user to systematically and non-linearly combine temporal and spatial information to predict the user’s displacement from their currently checked-in location to the next one. The locations whose distances to the user’s current checked-in location are the closest to the predicted displacement are recommended. We also propose an enhancement to take into account category information of locations for semantic-aware recommendation. A unified recommendation framework called spatial–temporal–semantic (STS) is introduced to combine displacement prediction and the semantic-aware enhancement to provide final top-N recommendation. Extensive experiments over real datasets show that the proposed STS framework significantly outperforms the state-of-the-art location recommendation models in terms of precision and mean reciprocal rank (MRR).

Стилі APA, Harvard, Vancouver, ISO та ін.

8

Huang, Xinlei, Zhiqi Ma, Dian Meng, et al. "PRAGA: Prototype-aware Graph Adaptive Aggregation for Spatial Multi-modal Omics Analysis." Proceedings of the AAAI Conference on Artificial Intelligence 39, no. 1 (2025): 326–33. https://doi.org/10.1609/aaai.v39i1.32010.

Повний текст джерела

Анотація:

Spatial multi-modal omics technology, highlighted by Nature Methods as an advanced biological technique in 2023, plays a critical role in resolving biological regulatory processes with spatial context. Recently, graph neural networks based on K-nearest neighbor (KNN) graphs have gained prominence in spatial multi-modal omics methods due to their ability to model semantic relations between sequencing spots. However, the fixed KNN graph fails to capture the latent semantic relations hidden by the inevitable data perturbations during the biological sequencing process, resulting in the loss of semantic information. In addition, the common lack of spot annotation and class number priors in practice further hinders the optimization of spatial multi-modal omics models. Here, we propose a novel spatial multi-modal omics resolved framework, termed Prototype-aware Graph Adaptative Aggregation for Spatial Multi-modal Omics Analysis (PRAGA). PRAGA constructs a dynamic graph to capture latent semantic relations and comprehensively integrate spatial information and feature semantics. The learnable graph structure can also denoise perturbations by learning cross-modal knowledge. Moreover, a dynamic prototype contrastive learning is proposed based on the dynamic adaptability of Bayesian Gaussian Mixture Models to optimize the multi-modal omics representations for unknown biological priors. Quantitative and qualitative experiments on simulated and real datasets with 7 competing methods demonstrate the superior performance of PRAGA.

Стилі APA, Harvard, Vancouver, ISO та ін.

9

Wang, Beibei, Youfang Lin, Shengnan Guo, and Huaiyu Wan. "GSNet: Learning Spatial-Temporal Correlations from Geographical and Semantic Aspects for Traffic Accident Risk Forecasting." Proceedings of the AAAI Conference on Artificial Intelligence 35, no. 5 (2021): 4402–9. http://dx.doi.org/10.1609/aaai.v35i5.16566.

Повний текст джерела

Анотація:

Traffic accident forecasting is of great importance to urban public safety, emergency treatment, and construction planning. However, it is very challenging since traffic accidents are affected by multiple factors, and have multi-scale dependencies on both spatial and temporal dimensional features. Meanwhile, traffic accidents are rare events, which leads to the zero-inflated issue. Existing traffic accident forecasting methods cannot deal with all above problems simultaneously. In this paper, we propose a novel model, named GSNet, to learn the spatial-temporal correlations from geographical and semantic aspects for traffic accident risk forecasting. In the model, a Spatial-Temporal Geographical Module is designed to capture the geographical spatial-temporal correlations among regions, while a Spatial-Temporal Semantic Module is proposed to model the semantic spatial-temporal correlations among regions. In addition, a weighted loss function is designed to solve the zero-inflated issue. Extensive experiments on two real-world datasets demonstrate the superiority of GSNet against the state-of-the-art baseline methods.

Стилі APA, Harvard, Vancouver, ISO та ін.

10

Shen, Xiang, Dezhi Han, Chongqing Chen, Gaofeng Luo, and Zhongdai Wu. "An effective spatial relational reasoning networks for visual question answering." PLOS ONE 17, no. 11 (2022): e0277693. http://dx.doi.org/10.1371/journal.pone.0277693.

Повний текст джерела

Анотація:

Visual Question Answering (VQA) is a method of answering questions in natural language based on the content of images and has been widely concerned by researchers. The existing research on the visual question answering model mainly focuses on the point of view of attention mechanism and multi-modal fusion. It only pays attention to the visual semantic features of the image in the process of image modeling, ignoring the importance of modeling the spatial relationship of visual objects. We are aiming at the existing problems of the existing VQA model research. An effective spatial relationship reasoning network model is proposed, which can combine visual object semantic reasoning and spatial relationship reasoning at the same time to realize fine-grained multi-modal reasoning and fusion. A sparse attention encoder is designed to capture contextual information effectively in the semantic reasoning module. In the spatial relationship reasoning module, the graph neural network attention mechanism is used to model the spatial relationship of visual objects, which can correctly answer complex spatial relationship reasoning questions. Finally, a practical compact self-attention (CSA) mechanism is designed to reduce the redundancy of self-attention in linear transformation and the number of model parameters and effectively improve the model’s overall performance. Quantitative and qualitative experiments are conducted on the benchmark datasets of VQA 2.0 and GQA. The experimental results demonstrate that the proposed method performs favorably against the state-of-the-art approaches. Our best single model has an overall accuracy of 71.18% on the VQA 2.0 dataset and 57.59% on the GQA dataset.

Стилі APA, Harvard, Vancouver, ISO та ін.

Більше джерел

Дисертації з теми "Spatial-semantic model"

1

Hale, Denise Ann. "The development of semantic memory : a spatial model of animal concepts in schoolchildren, novices and experts." Thesis, London Metropolitan University, 1991. http://repository.londonmet.ac.uk/3390/.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

2

Cribbin, Timothy Frederick. "Classifying complex topics using spatial-semantic document visualization : an evaluation of an interaction model to support open-ended search tasks." Thesis, Brunel University, 2005. http://bura.brunel.ac.uk/handle/2438/3296.

Повний текст джерела

Анотація:

In this dissertation we propose, test and develop a novel search interaction model to address two key problems associated with conducting an open-ended search task within a classical information retrieval system: (i) the need to reformulate the query within the context of a shifting conception of the problem and (ii) the need to integrate relevant results across a number of separate results sets. In our model the user issues just one highrecall query and then performs a sequence of more focused, distinct aspect searches by browsing the static structured context of a spatial-semantic visualization of this retrieved document set. Our thesis is that unsupervised spatial-semantic visualization can automatically classify retrieved documents into a two-level hierarchy of relevance. In particular we hypothesise that the locality of any given aspect exemplar will tend to comprise a sufficient proportion of same-aspect documents to support a visually guided strategy for focused, same-aspect searching that we term the aspect cluster growing strategy. We examine spatial-semantic classification and potential aspect cluster growing performance across three scenarios derived from topics and relevance judgements from the TREC test collection. Our analyses show that the expected classification can be represented in spatial-semantic structures created from document similarities computed by a simple vector space text analysis procedure. We compare two diametrically opposed approaches to layout optimisation: a global approach that focuses on preserving the all similarities and a local approach that focuses only on the strongest similarities. We find that the local approach, based on a minimum spanning tree of similarities, produces a better classification and, as observed from strategy simulation, more efficient aspect cluster growing performance in most situations, compared to the global approach of multidimensional scaling. We show that a small but significant proportion of aspect clustering growing cases can be problematic, regardless of the layout algorithm used. We identify the characteristics of these cases and, on this basis, demonstrate a set of novel interactive tools that provide additional semantic cues to aid the user in locating same-aspect documents.

Стилі APA, Harvard, Vancouver, ISO та ін.

3

Солонская, Светлана Владимировна. "Модели, метод и информационная технология обработки сигналов в интеллектуальных радиолокационных комплексах". Thesis, Харьковский национальный университет радиоэлектроники, 2016. http://repository.kpi.kharkov.ua/handle/KhPI-Press/23588.

Повний текст джерела

Анотація:

Диссертация на соискание ученой степени кандидата технических наук по специальности 05.13.06 – информационные технологии. – Национальный технический университет "Харьковский политехнический институт", Харьков, 2016. Диссертация посвящена решению научно-практической задачи разработки метода для повышения эффективности обнаружения и распознавания сигналов в радиолокационных комплексах путем интеллектуализации обработки сигнальной информации. В работе проанализированы научные достижения в области обработки сигналов, определены задачи обработки сигналов и подходы к их решению. В технологии обработки радиолокационных сигналов предложено выделить два этапа: внутриобзорная и междуобзорная обработка сигналов. На основе данного подхода разработаны спектрально-семантическая и пространственно-семантическая модели обработки радиолокационных сигналов. В работе усовершенствован метод формализации процессов восприятия и преобразования сигналов и сигнальных образов, который основан на компараторной идентификации, и позволяет определять семантическую составляющую сигналов и сигнальных образов на этапе предварительной обработки информации. Предложена реализация информационной технологии обработки сигналов в интеллектуальных радиолокационных комплексах с учетом спектрально-семантической и пространственно-семантической моделей. Данный подход позволяет моделировать процессы обработки и распознавания радиолокационных сигналов и сигнальных образов средствами алгебры конечных предикатов. На этапе внутриобзорной обработки сигналов и сигнальных образов объекты классифицируются по спектральному образу с помощью спектрально-семантической модели. Предварительная обработка пачки сигналов основана на формировании предикатной формы спектрального образа, затем на ее основе определяются значения признаков, и осуществляется идентификация объекта. На этапе междуобзорной обработки сигналов для уточнения результатов идентификации объектов используется пространственно-семантическая модель. Рассматривается система дискретных выборок – элементов обработки по дальности и азимуту. Для описания ситуации вокруг анализируемого в данный момент элемента изображения (элемента зоны обзора РЛС), вводится система предикатных признаков. По оценке значений признаков в каждом элементе обработки и полученным предикатным уравнениям определяется воздушный объект. Предложенная модель позволяет определять отметки воздушных объектов на фоне мешающих отражений и наблюдать динамику изменения в течение нескольких обзоров РЛС.<br>Thesis for a candidate degree in technical science, specialty 05.13.06 – Information Technologies. – National Technical University "Kharkiv Polytechnic Institute". – Kharkiv, 2016. This thesis deals with a topical theoretical and practical task to improve the efficiency of information technologies for the processing and identifying of radar signals. Scientific achievements in signal processing are analysed, tasks to process signals and approaches to their solution are determined in the thesis. It is proposed to distinguish two stages in the technology of radar signal processing: intrasurveillance and intersurveillance signal processing. On the basis of this approach, spectral-semantic and spatial-semantic models are developed. Testing and the evaluation of the research results, which are based on the information technology developed, are made. The results are put into practice in: the module of multisurveillance processing of radar signals and data for surveillance radars of the Ministry of Defence of Ukraine; the research project Development of Systems of Radiomonitoring and Passive Direction Finding; Scientific Production Firm Optima Ltd.; an educational process of the Department of Information Technologies and Mechatronics in Kharkov National Automobile and Highway University.

Стилі APA, Harvard, Vancouver, ISO та ін.

4

Солонська, Світлана Володимирівна. "Моделі, метод та інформаційна технологія обробки сигналів в інтелектуальних радіолокаційних комплексах". Thesis, НТУ "ХПІ", 2016. http://repository.kpi.kharkov.ua/handle/KhPI-Press/23586.

Повний текст джерела

Анотація:

Дисертація на здобуття наукового ступеня кандидата технічних наук за спеціальністю 05.13.06 – інформаційні технології. – Національний технічний університет "Харківський політехнічний інститут", Харків, 2016. У дисертаційній роботі вирішена науково-практична задача розроблення методу для підвищення ефективності виявлення та розпізнавання сигналів в радіолокаційних комплексах шляхом інтелектуалізації обробки сигнальної інформації. У роботі проаналізовано наукові досягнення в галузі обробки сигналів, визначено задачі обробки сигналів та підходи до їх вирішення. У технології обробки радіолокаційних сигналів запропоновано виділити два етапи: внутрішньооглядова й міжоглядова обробка сигналів. На основі цього підходу створено спектрально-семантичну і просторово-семантичну моделі обробки радіолокаційних сигналів. Проведено апробацію й оцінку ефективності результатів дослідження, отриманих на базі розробленої інформаційної технології. Результати впроваджено в модулі багатооглядової обробки радіолокаційних сигналів та інформації для оглядових РЛС МО України, у науково-дослідному проекті "Розробка систем радіоконтролю, радіомоніторингу та систем пасивної пеленгації" ТОВ НПФ "Оптима", а також у навчальний процес кафедри інформаційних технологій та мехатроніки ХНАДУ.<br>Thesis for a candidate degree in technical science, specialty 05.13.06 – Information Technologies. – National Technical University "Kharkiv Polytechnic Institute". – Kharkiv, 2016. This thesis deals with a topical theoretical and practical task to improve the efficiency of information technologies for the processing and identifying of radar signals. Scientific achievements in signal processing are analysed, tasks to process signals and approaches to their solution are determined in the thesis. It is proposed to distinguish two stages in the technology of radar signal processing: intrasurveillance and intersurveillance signal processing. On the basis of this approach, spectral-semantic and spatial-semantic models are developed. Testing and the evaluation of the research results, which are based on the information technology developed, are made. The results are put into practice in: the module of multisurveillance processing of radar signals and data for surveillance radars of the Ministry of Defence of Ukraine; the research project Development of Systems of Radiomonitoring and Passive Direction Finding; Scientific Production Firm Optima Ltd.; an educational process of the Department of Information Technologies and Mechatronics in Kharkov National Automobile and Highway University.

Стилі APA, Harvard, Vancouver, ISO та ін.

5

Farrugia, James A. "Semantic Interoperability of Geospatial Ontologies: A Model-theoretic Analysis." Fogler Library, University of Maine, 2007. http://www.library.umaine.edu/theses/pdf/FarrugiaJA2007.pdf.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

6

Kvasova, Daria 1989. "The Role of cross-modal semantic interactions in real-world visuo-spatial attention." Doctoral thesis, Universitat Pompeu Fabra, 2020. http://hdl.handle.net/10803/668665.

Повний текст джерела

Анотація:

In our everyday life we must effectively orient attention to relevant objects and events in multisensory environments. The impact of cross-modal links for attention orienting to spatial and temporal cues has been widely described. However, real-life scenarios provide a rich web of semantic information through the different sensory modalities. Despite some previous studies have revealed an impact of crossmodal sematic correspondences, the results are mixed with regard to the conditions in which audiovisual semantic congruence can influence attention orienting. Furthermore, the vast majority of the research on crossmodal semantics used simple, stereotyped displays that are far from achieving ecological validity. The present thesis attempts to close this gap by addressing the role of identity-based crossmodal relationships on attention orienting in scenarios closer to real-world conditions. To this end, the experiments presented here attempt to extrapolate and generalize previous findings in more realistic environments by using naturalistic and dynamic stimuli, and address the theoretical questions of task relevance and perceptual load. The outcome of the three empirical studies in this thesis lead to several conclusions. First, that the effect of audio-visual semantic congruence on attention is not strictly automatic. Instead, they suggest that some top-down processing is necessary for audio-visual semantic congruence to trigger spatial orienting. The second conclusion to emerge is that crossmodal semantic congruence can guide attention under goal-directed conditions in visual search, and also under free observation in complex and dynamic scenes. Third, that perceptual load is a limiting factor for these interactions. These findings extend previous knowledge on object-based crossmodal interactions with simple stimuli and clarify how audio-visual semantically congruent relationships play out in realistic scenarios.<br>En nuestra vida cotidiana debemos orientar efectivamente la atención a objetos y eventos relevantes en entornos multisensoriales. El impacto que tienen los enlaces intermodales en la orientación de la atención a señales espaciales y temporales ha sido ampliamente descrito. Sin embargo, los escenarios de la vida real proporcionan una rica red de información semántica a través de las diferentes modalidades sensoriales. A pesar de que algunos estudios previos han revelado un impacto de las correspondencias semánticas entre modalidades, los resultados se mezclan con respecto a las condiciones en que la congruencia semántica audiovisual puede influir en la orientación de la atención. Además, la gran mayoría de la investigación sobre semántica intermodal utilizó representaciones simples y estereotipadas que están lejos de alcanzar la validez ecológica. La presente tesis intenta llenar esta brecha al abordar el papel que las relaciones intermodales basadas en la identidad tienen en la orientación de la atención en escenarios más cercanos a las condiciones del mundo real. Con este fin, los experimentos presentados aquí intentan extrapolar y generalizar hallazgos previos en entornos más realistas mediante el uso de estímulos naturales y dinámicos, y abordar cuestiones teóricas como la relevancia de la tarea y la carga perceptiva. El resultado de los tres estudios empíricos de esta tesis condujo a varias conclusiones. Primero, que el efecto de la congruencia semántica audiovisual en la atención no es estrictamente automático. En cambio, sugieren que es necesario un procesamiento de arriba hacia abajo para que la congruencia semántica audiovisual desencadene en la orientación espacial. La segunda conclusión que surge es que la congruencia semántica intermodal puede guiar la atención en condiciones de búsqueda visual dirigida a un objetivo, y también bajo observación libre en escenas complejas y dinámicas. Tercero, la carga perceptiva es un factor limitante para estas interacciones. Estos hallazgos amplían el conocimiento previo sobre las interacciones intermodales basadas en objetos usando estímulos simples y aclaran cómo las relaciones audiovisuales semánticamente congruentes se desarrollan en escenarios realista

Стилі APA, Harvard, Vancouver, ISO та ін.

7

Kang, Hyunmo. "Managing and exploring media using semantic regions a spatial interface supporting user-defined mental models /." College Park, Md. : University of Maryland, 2003. http://hdl.handle.net/1903/48.

Повний текст джерела

Анотація:

Thesis (Ph. D.) -- University of Maryland, College Park, 2003.<br>Thesis research directed by: Computer Science. Title from t.p. of PDF. Includes bibliographical references. Published by UMI Dissertation Services, Ann Arbor, Mich. Also available in paper.

Стилі APA, Harvard, Vancouver, ISO та ін.

8

Chen, Xi. "Learning with Sparcity: Structures, Optimization and Applications." Research Showcase @ CMU, 2013. http://repository.cmu.edu/dissertations/228.

Повний текст джерела

Анотація:

The development of modern information technology has enabled collecting data of unprecedented size and complexity. Examples include web text data, microarray & proteomics, and data from scientific domains (e.g., meteorology). To learn from these high dimensional and complex data, traditional machine learning techniques often suffer from the curse of dimensionality and unaffordable computational cost. However, learning from large-scale high-dimensional data promises big payoffs in text mining, gene analysis, and numerous other consequential tasks. Recently developed sparse learning techniques provide us a suite of tools for understanding and exploring high dimensional data from many areas in science and engineering. By exploring sparsity, we can always learn a parsimonious and compact model which is more interpretable and computationally tractable at application time. When it is known that the underlying model is indeed sparse, sparse learning methods can provide us a more consistent model and much improved prediction performance. However, the existing methods are still insufficient for modeling complex or dynamic structures of the data, such as those evidenced in pathways of genomic data, gene regulatory network, and synonyms in text data. This thesis develops structured sparse learning methods along with scalable optimization algorithms to explore and predict high dimensional data with complex structures. In particular, we address three aspects of structured sparse learning: 1. Efficient and scalable optimization methods with fast convergence guarantees for a wide spectrum of high-dimensional learning tasks, including single or multi-task structured regression, canonical correlation analysis as well as online sparse learning. 2. Learning dynamic structures of different types of undirected graphical models, e.g., conditional Gaussian or conditional forest graphical models. 3. Demonstrating the usefulness of the proposed methods in various applications, e.g., computational genomics and spatial-temporal climatological data. In addition, we also design specialized sparse learning methods for text mining applications, including ranking and latent semantic analysis. In the last part of the thesis, we also present the future direction of the high-dimensional structured sparse learning from both computational and statistical aspects.

Стилі APA, Harvard, Vancouver, ISO та ін.

9

CAPOBIANCO, ROBERTO. "Interactive generation and learning of semantic-driven robot behaviors." Doctoral thesis, 2017. http://hdl.handle.net/11573/942393.

Повний текст джерела

Анотація:

The generation of adaptive and reflexive behavior is a challenging task in artificial intelligence and robotics. In this thesis, we develop a framework for knowledge representation, acquisition, and behavior generation that explicitly incorporates semantics, adaptive reasoning and knowledge revision. By using our model, semantic information can be exploited by traditional planning and decision making frameworks to generate empirically effective and adaptive robot behaviors, as well as to enable complex but natural human-robot interactions. In our work, we introduce a model of semantic mapping, we connect it with the notion of affordances, and we use those concepts to develop semantic-driven algorithms for knowledge acquisition, update, learning and robot behavior generation. In particular, we apply such models within existing planning and decision making frameworks to achieve semantic-driven and adaptive robot behaviors in a generic environment. On the one hand, this work generalizes existing semantic mapping models and extends them to include the notion of affordances. On the other hand, this work integrates semantic information within well-defined long-term planning and situated action frameworks to effectively generate adaptive robot behaviors. We validate our approach by evaluating it on a number of problems and robot tasks. In particular, we consider service robots deployed in interactive and social domains, such as offices and domestic environments. To this end, we also develop prototype applications that are useful for evaluation purposes.

Стилі APA, Harvard, Vancouver, ISO та ін.

Книги з теми "Spatial-semantic model"

1

Regier, Terry. The human semantic potential: Spatial language and constrained connectionism. MIT Press, 1996.

Знайти повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

2

Regier, Terry. Human Semantic Potential: Spatial Language and Constrained Connectionism. MIT Press, 2019.

Знайти повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

3

Vallar, Giuseppe, and Nadia Bolognini. Unilateral Spatial Neglect. Edited by Anna C. (Kia) Nobre and Sabine Kastner. Oxford University Press, 2014. http://dx.doi.org/10.1093/oxfordhb/9780199675111.013.012.

Повний текст джерела

Анотація:

Left unilateral spatial neglect is the most frequent and disabling neuropsychological syndrome caused by lesions to the right hemisphere. Over 50% of right-brain-damaged patients show neglect, while right neglect after left-hemispheric damage is less frequent. Neglect patients are unable to orient towards the side contralateral to the lesion, to detect and report sensory events in that portion of space, as well as to explore it by motor action. Neglect is a multicomponent disorder, which may involve the contralesional side of the body or of extra-personal physical or imagined space, different sensory modalities, specific domains (e.g. ‘neglect dyslexia’), and worsen sensorimotor deficits. Neglect is due to higher-order unilateral deficits of spatial attention and representation, so that patients are not aware of contralesional events, which, however, undergo a substantial amount of unconscious processing up to the semantic level. Cross-modal sensory integration is also largely preserved. Neglect is primarily a spatially specific disorder of perceptual consciousness. The responsible lesions involve a network including the fronto-temporo-parietal cortex (particularly the posterior-inferior parietal lobe, at the temporo-parietal junction), their white matter connections, and some subcortical grey nuclei (thalamus, basal ganglia). Damage to primary sensory and motor regions is not associated to neglect. A variety of physiological lateralized and asymmetrical sensory stimulations (vestibular, optokinetic, prism adaptation, motor activation), and transcranial electrical and magnetic stimulations, may temporarily improve or worsen neglect. Different procedures have been successfully developed to rehabilitate neglect, using both ‘top down’ (training the voluntary orientation of attention) and ‘bottom up’ (the above-mentioned stimulations) approaches.

Стилі APA, Harvard, Vancouver, ISO та ін.

Частини книг з теми "Spatial-semantic model"

1

Harbelot, Benjamin, Helbert Arenas, and Christophe Cruz. "A Semantic Model to Query Spatial–Temporal Data." In Lecture Notes in Geoinformation and Cartography. Springer Berlin Heidelberg, 2013. http://dx.doi.org/10.1007/978-3-642-31833-7_5.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

2

Ouni, Achref, Thierry Chateau, Eric Royer, Marc Chevaldonné, and Michel Dhome. "A New CBIR Model Using Semantic Segmentation and Fast Spatial Binary Encoding." In Computational Collective Intelligence. Springer International Publishing, 2022. http://dx.doi.org/10.1007/978-3-031-16014-1_35.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

3

Phan, T. V., G. T. Anh Nguyen, and Trung Tran Do Quoc. "Management of Buildings with Semantic and 3D Spatial Properties by S_EUDM Data Model." In Lecture Notes in Civil Engineering. Springer Singapore, 2020. http://dx.doi.org/10.1007/978-981-15-5144-4_89.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

4

Grisiute, Ayda, Heidi Silvennoinen, Shiying Li, et al. "A Semantic Spatial Policy Model to Automatically Calculate Allowable Gross Floor Areas in Singapore." In Communications in Computer and Information Science. Springer Nature Switzerland, 2023. http://dx.doi.org/10.1007/978-3-031-37189-9_30.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

5

Koner, Rajat, Hang Li, Marcel Hildebrandt, Deepan Das, Volker Tresp, and Stephan Günnemann. "Graphhopper: Multi-hop Scene Graph Reasoning for Visual Question Answering." In The Semantic Web – ISWC 2021. Springer International Publishing, 2021. http://dx.doi.org/10.1007/978-3-030-88361-4_7.

Повний текст джерела

Анотація:

AbstractVisual Question Answering (VQA) is concerned with answering free-form questions about an image. Since it requires a deep semantic and linguistic understanding of the question and the ability to associate it with various objects that are present in the image, it is an ambitious task and requires multi-modal reasoning from both computer vision and natural language processing. We propose Graphhopper, a novel method that approaches the task by integrating knowledge graph reasoning, computer vision, and natural language processing techniques. Concretely, our method is based on performing context-driven, sequential reasoning based on the scene entities and their semantic and spatial relationships. As a first step, we derive a scene graph that describes the objects in the image, as well as their attributes and their mutual relationships. Subsequently, a reinforcement learning agent is trained to autonomously navigate in a multi-hop manner over the extracted scene graph to generate reasoning paths, which are the basis for deriving answers. We conduct an experimental study on the challenging dataset GQA, based on both manually curated and automatically generated scene graphs. Our results show that we keep up with human performance on manually curated scene graphs. Moreover, we find that Graphhopper outperforms another state-of-the-art scene graph reasoning model on both manually curated and automatically generated scene graphs by a significant margin.

Стилі APA, Harvard, Vancouver, ISO та ін.

6

Wang, Jun, Qinling Dai, Leiguang Wang, Yili Zhao, Haoyu Fu, and Yue Zhang. "High Spatial Resolution Remote Sensing Imagery Classification Based on Markov Random Field Model Integrating Granularity and Semantic Features." In Pattern Recognition and Computer Vision. Springer Nature Switzerland, 2022. http://dx.doi.org/10.1007/978-3-031-18913-5_39.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

7

Van Pham, Dang. "Proposing Spatial - Temporal - Semantic Data Model Managing Genealogy and Space Evolution History of Objects in 3D Geographical Space." In Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering. Springer International Publishing, 2021. http://dx.doi.org/10.1007/978-3-030-67101-3_13.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

8

Sanderson, Edward, and Bogdan J. Matuszewski. "FCN-Transformer Feature Fusion for Polyp Segmentation." In Medical Image Understanding and Analysis. Springer International Publishing, 2022. http://dx.doi.org/10.1007/978-3-031-12053-4_65.

Повний текст джерела

Анотація:

AbstractColonoscopy is widely recognised as the gold standard procedure for the early detection of colorectal cancer (CRC). Segmentation is valuable for two significant clinical applications, namely lesion detection and classification, providing means to improve accuracy and robustness. The manual segmentation of polyps in colonoscopy images is time-consuming. As a result, the use of deep learning (DL) for automation of polyp segmentation has become important. However, DL-based solutions can be vulnerable to overfitting and the resulting inability to generalise to images captured by different colonoscopes. Recent transformer-based architectures for semantic segmentation both achieve higher performance and generalise better than alternatives, however typically predict a segmentation map of $$\frac{h}{4}\times \frac{w}{4}$$ h 4 × w 4 spatial dimensions for a $$h\times w$$ h × w input image. To this end, we propose a new architecture for full-size segmentation which leverages the strengths of a transformer in extracting the most important features for segmentation in a primary branch, while compensating for its limitations in full-size prediction with a secondary fully convolutional branch. The resulting features from both branches are then fused for final prediction of a $$h\times w$$ h × w segmentation map. We demonstrate our method’s state-of-the-art performance with respect to the mDice, mIoU, mPrecision, and mRecall metrics, on both the Kvasir-SEG and CVC-ClinicDB dataset benchmarks. Additionally, we train the model on each of these datasets and evaluate on the other to demonstrate its superior generalisation performance.Code available: https://github.com/CVML-UCLan/FCBFormer.

Стилі APA, Harvard, Vancouver, ISO та ін.

9

Hu, Yao, JiaHong Yang, YaQin Wang, and LiuMing Xiao. "Multi-modal Variable-Channel Spatial-Temporal Semantic Action Recognition Network." In Communications in Computer and Information Science. Springer Nature Singapore, 2024. http://dx.doi.org/10.1007/978-981-97-8749-4_10.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

10

Kolbe, Thomas H., and Andreas Donaubauer. "Semantic 3D City Modeling and BIM." In Urban Informatics. Springer Singapore, 2021. http://dx.doi.org/10.1007/978-981-15-8983-6_34.

Повний текст джерела

Анотація:

AbstractSemantic 3D city modeling and building information modeling (BIM) are methods for modeling, creating, and analyzing three-dimensional representations of physical objects of the environment. Digital modeling of the built environment has been approached from at least four different domains: computer graphics and gaming, planning and construction, urban simulation, and geomatics. This chapter introduces the similarities and differences of 3D models from these disciplines with regard to aspects like scale, level of detail, representation of spatial and semantic characteristics, and appearance. Exemplified by the international standards CityGML and Industry Foundation Classes (IFC), information models from semantic 3D city modeling and BIM and their corresponding modeling approaches are explored, and the relationships between them are discussed. Based on use cases from infrastructure planning, approaches for integrating information from semantic 3D city modeling and BIM, such as semantic transformation between CityGML and IFC, are described. Furthermore, the role of semantic 3D city modeling and BIM for recent developments in urban informatics, such as smart cities and digital twins, is investigated and illustrated by real-world examples.

Стилі APA, Harvard, Vancouver, ISO та ін.

Тези доповідей конференцій з теми "Spatial-semantic model"

1

Farsijani, Fatemeh, Ali Zaheri, Davar Giveki, and Hossein Peyvandi. "Low-Level Feature Representation in the RCSU-Net Model Using Channel-Spatial Attention Mechanism for Semantic Segmentation of Plant Leaves." In 2025 29th International Computer Conference, Computer Society of Iran (CSICC). IEEE, 2025. https://doi.org/10.1109/csicc65765.2025.10967433.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

2

Wang, Haoxiang, Pavan Kumar Anasosalu Vasu, Fartash Faghri, et al. "SAM-CLIP: Merging Vision Foundation Models towards Semantic and Spatial Understanding." In 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). IEEE, 2024. http://dx.doi.org/10.1109/cvprw63382.2024.00367.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

3

Kent, Lee, Hermenegildo Solheiro, and Keisuke Toyoda. "Multiple Multi-Modal AI for Semantic Annotations of 3D Spatial Data." In 20th International Conference on Computer Graphics Theory and Applications. SCITEPRESS - Science and Technology Publications, 2025. https://doi.org/10.5220/0013235300003912.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

4

Wang, Xiaolin, and Yingwei Luo. "Model semantic network for massive spatial information." In IGARSS 2011 - 2011 IEEE International Geoscience and Remote Sensing Symposium. IEEE, 2011. http://dx.doi.org/10.1109/igarss.2011.6049835.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

5

Li, Shiqi, Tiejun Zhao, and Hanjing Li. "Improving Spatial Semantic Analysis by a Combining Model." In 2010 International Conference on E-Business and E-Government (ICEE). IEEE, 2010. http://dx.doi.org/10.1109/icee.2010.363.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

6

Chen, Ying Dong, Rong Guo Chen, Zhen Lin Liu, Zhen Chen, Zhan Wei Lu, and Min Qiang Fan. "Creation of Spatial Information Service Semantic Topology Description Model." In 2009 1st International Conference on Information Science and Engineering (ICISE 2009). IEEE, 2009. http://dx.doi.org/10.1109/icise.2009.439.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

7

Memar, Sara, Mohammadreza Ektefa, and Lilly Suriani Affendey. "Developing context model supporting spatial relations for semantic video retrieval." In Knowledge Management (CAMP). IEEE, 2010. http://dx.doi.org/10.1109/infrkm.2010.5466951.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

8

Yu, Feiyang, and Horace S Ip. "Automatic Semantic Annotation of Images using Spatial Hidden Markov Model." In 2006 IEEE International Conference on Multimedia and Expo. IEEE, 2006. http://dx.doi.org/10.1109/icme.2006.262459.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

9

Yan, Y., J. Li, and Z. He. "Research on Ontology Based Semantic Integration Model in Spatial Data Sharing." In 2006 IEEE International Symposium on Geoscience and Remote Sensing. IEEE, 2006. http://dx.doi.org/10.1109/igarss.2006.738.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

10

Wang, Xingang, Kuo Guo, and Zhigang Gai. "A Semi-Formal Multi-Policy Secure Model for Semantic Spatial Trajectories." In the 2017 International Conference. ACM Press, 2017. http://dx.doi.org/10.1145/3058060.3058063.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

Звіти організацій з теми "Spatial-semantic model"

1

Patwa, B., P. L. St-Charles, G. Bellefleur, and B. Rousseau. Predictive models for first arrivals on seismic reflection data, Manitoba, New Brunswick, and Ontario. Natural Resources Canada/CMSS/Information Management, 2022. http://dx.doi.org/10.4095/329758.

Повний текст джерела

Анотація:

First arrivals are the primary waves picked and analyzed by seismologists to infer properties of the subsurface. Here we try to solve a problem in a small subsection of the seismic processing workflow: first break picking of seismic reflection data. We formulate this problem as an image segmentation task. Data is preprocessed, cleaned from outliers and extrapolated to make the training of deep learning models feasible. We use Fully Convolutional Networks (specifically UNets) to train initial models and explore their performance with losses, layer depths, and the number of classes. We propose to use residual connections to improve each UNet block and residual paths to solve the semantic gap between UNet encoder and decoder which improves the performance of the model. Adding spatial information as an extra channel helped increase the RMSE performance of the first break predictions. Other techniques like data augmentation, multitask loss, and normalization methods, were further explored to evaluate model improvement.

Стилі APA, Harvard, Vancouver, ISO та ін.

Ми пропонуємо знижки на всі преміум-плани для авторів, чиї праці увійшли до тематичних добірок літератури. Зв'яжіться з нами, щоб отримати унікальний промокод!