To see the other types of publications on this topic, follow the link: MAMBA.
Journal articles on the topic 'MAMBA'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 journal articles for your research on the topic 'MAMBA.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse journal articles on a wide variety of disciplines and organise your bibliography correctly.
1
Quarch, Verena, Lukas Brander, and Luca Cioccari. "An Unexpected Case of Black Mamba (Dendroaspis polylepis) Bite in Switzerland." Case Reports in Critical Care 2017 (2017): 1–3. http://dx.doi.org/10.1155/2017/5021924.
Full textAbstract:
Mambas (genusDendroaspis) are among the most feared venomous African snakes. Without medical treatment, mamba bites are frequently fatal. First-aid treatment includes lymphatic retardation with the pressure immobilization technique. Medical management comprises continuous monitoring, securing patency of the airway, ensuring adequate ventilation, symptomatic measures, and administration of specific antivenin. We report an unusual case of a snake breeder bitten by a black mamba in Switzerland, report the clinical course, and review the lifesaving emergency management of mamba bites. This case highlights the importance of early antivenin administration and suggests that emergency and critical care physicians as well as first responders all around the world should be familiar with clinical toxinology of exotic snake bites as well as with the logistics to most rapidly make the specific antivenin available.
2
Xiao, Haoke, Lv Tang, Peng-tao Jiang, Hao Zhang, Jinwei Chen, and Bo Li. "Boosting Vision State Space Model with Fractal Scanning." Proceedings of the AAAI Conference on Artificial Intelligence 39, no. 8 (2025): 8646–54. https://doi.org/10.1609/aaai.v39i8.32934.
Full textAbstract:
Recently, foundational models have significantly advanced in different tasks, accompanied by Transformer as the general backbone. However, Transformer's quadratic complexity poses challenges for handling longer sequences and higher resolution images, which may limit foundational models further development. To alleviate this issue, various efficient State Space Models (SSMs) like Mamba have emerged, initially matching Transformer performance and gradually surpassing it. To improve the performance of SSMs in computer vision tasks, one crucial viewpoint is effective serialization of images. Existing vision Mambas, which rely on a linear scanning mechanism, often struggle to capture complex spatial relationships in 2D images. This results in feature loss during serialization and negatively impacts model performance. To overcome this limitation, we propose the use of fractal scanning curves for image serialization to enhance the Mambas’ ability to accurately model complex spatial dependencies. Additionally, unlike existing vision Mambas, which are designed with various curve scanning directions that increase the complexity, contradicting the original intent of Mamba to enhance model performance. We novelty introduce the Fractal Fusion Pathway (FFP) for our FractalMamba, which can enhance its performance efficiently. Extensive experiments underscore the superiority of our proposed FractalMamba.
3
Nielsen, Vance G., Michael T. Wagner, and Nathaniel Frank. "Mechanisms Responsible for the Anticoagulant Properties of Neurotoxic Dendroaspis Venoms: A Viscoelastic Analysis." International Journal of Molecular Sciences 21, no. 6 (2020): 2082. http://dx.doi.org/10.3390/ijms21062082.
Full textAbstract:
Using thrombelastography to gain mechanistic insights, recent investigations have identified enzymes and compounds in Naja and Crotalus species’ neurotoxic venoms that are anticoagulant in nature. The neurotoxic venoms of the four extant species of Dendroaspis (the Black and green mambas) were noted to be anticoagulant in nature in human blood, but the mechanisms underlying these observations have never been explored. The venom proteomes of these venoms are unique, primarily composed of three finger toxins (3-FTx), Kunitz-type serine protease inhibitors (Kunitz-type SPI) and <7% metalloproteinases. The anticoagulant potency of the four mamba venoms available were determined in human plasma via thrombelastography; vulnerability to inhibition of anticoagulant activity to ethylenediaminetetraacetic acid (EDTA) was assessed, and inhibition of anticoagulant activity after exposure to a ruthenium (Ru)-based carbon monoxide releasing molecule (CORM-2) was quantified. Black mamba venom was the least potent by more than two orders of magnitude compared to the green mamba venoms tested; further, Black Mamba venom anticoagulant activity was not inhibited by either EDTA or CORM-2. In contrast, the anticoagulant activities of the green mamba venoms were all inhibited by EDTA to a greater or lesser extent, and all had anticoagulation inhibited with CORM-2. Critically, CORM-2-mediated inhibition was independent of carbon monoxide release, but was dependent on a putative Ru-based species formed from CORM-2. In conclusion, there was great species-specific variation in potency and mechanism(s) responsible for the anticoagulant activity of Dendroaspis venom, with perhaps all three protein classes—3-FTx, Kunitz-type SPI and metalloproteinases—playing a role in the venoms characterized.
4
Luiselli, Luca, Francesco M. Angelici, and Godfrey C. Akani. "Large elapids and arboreality: the ecology of Jameson’s green mamba (Dendroaspis jamesoni) in an Afrotropical forested region." Contributions to Zoology 69, no. 3 (2000): 147–55. http://dx.doi.org/10.1163/18759866-06903001.
Full textAbstract:
Several aspects of the ecology of Jameson’s green mamba Dendroaspis jamesoni jamesoni (Traill, 1843), a large-sized arboreal elapid snake, are studied in southern Nigeria. This species is common and widespread in the region studied. On the basis of the analysis of both the habitats of capture of the various specimens and the results of a logistical regression model, it seems that this species inhabits a wide variety of habitats (including secondary forest patches and the plantation-forest mosaic), and that its local distribution is not influenced by the presence of any macrohabitat parameter. Green mambas were observed both in the dry and in the wet season, without any statistical bias toward a particular season. Adult sex-ratio was approximately 1 : 1. Males were significantly longer than females. All adult mamba dietary records involved warm-blooded prey (mainly birds), whereas young mambas fed also upon lizards and toads. Nearly all the prey eaten by adult mambas were arboreal, and thus there was no support for the recent hypothesis that adult mambas develop an orientation to forage on terrestrial rodents. Male-male combats and matings were observed in December, January, and February (dry season), and gravid females were collected in April, May, and June (wet season). Females produced 7-16 eggs (mean 10.9), and litter size was Positively correlated with maternal length.
5
Hinds, M. J., C. M. Jolly, R. G. Nelson, Y. Donis, and E. Prophete. "Consumer Acceptability and Physicochemical Properties of Haitian Peanut Butter-Type Products (Mambas) Compared with U.S. Peanut Butter." Peanut Science 29, no. 2 (2002): 102–9. http://dx.doi.org/10.3146/pnut.29.2.0005.
Full textAbstract:
Abstract Small-scale food processors in Haiti manufacture peanut butter-type products, locally called mambas. Mambas are prepared from ground, roasted peanuts, and may be flavored with sugar or pimiento peppers, but contain no stabilizers. This study compared acceptability by Haitian consumers and some physicochemical properties of mambas and U.S. peanut butter. Three types of mambas—Plain (no sugar or salt added), Sucre (with sugar and salt), and Pimente (with crushed pimiento peppers and salt)—and U.S. Crystal® smooth peanut butter were evaluated by 199 panelists ranging in age from 14 to 77 yr, and from three urban districts in Haiti. A randomized complete block design was used for the study. Samples in souffle cups were labeled with three-digit random codes. Panelists indicated their feelings about intensity levels of color, oily appearance, peanut flavor, sweetness, spiciness, and smooth mouth feel of the samples on five-point Just-About-Right scales. Color of the U.S. peanut butter (U.S., h° = 73.1 ± 0.70, L value = 58.9 ± 0.60) and mamba sucre (MS, h° = 74.0 ± 0.72, L value = 57.6 ± 0.74) was considered Just-Right (JR) by 67 and 57% of panelists, respectively, but the mamba pimente (MP, h° = 78.0 ± 1.27, L value = 60.4 ± 2.21) was too pale (63%). Oily appearance of all products was acceptable to 51-59% of the participants. The peanut flavor of U.S., MS, and MP was JR for 77, 80, and 74% of panelists, respectively, whereas it was too low in the plain mamba (M) for 41% of the panelists. Sixty-six and 67%, respectively, of panelists liked the sweetness of U.S. and MS, but M and MP were not sweet enough for 72 and 68%, respectively, of the panelists. Products U.S., MS, M, and MP contained 9.4 ± 0.29, 11.6 ± 0.30, 4.7 ± 0.08, and 3.7 ± 0.34% sugar, respectively. Fifty-five percent of panelists indicated that the spiciness of MP was JR, whereas 82-92% felt that the other products were not spicy enough. Panelists (63-75%) felt that the products had an acceptable mouth feel, but MS and MP were liked the most (75%). Results indicate that Haitian consumers prefer mambas that have sweet and pimiento flavors to unflavored products.
6
Zhou, Weilian, Sei-ichiro Kamata, Haipeng Wang, Man Sing Wong, and Huiying (Cynthia) Hou. "Mamba-in-Mamba: Centralized Mamba-Cross-Scan in Tokenized Mamba Model for Hyperspectral image classification." Neurocomputing 613 (January 2025): 128751. http://dx.doi.org/10.1016/j.neucom.2024.128751.
Full text
7
Sariakarandria. "Mamba." Africultures 55, no. 2 (2003): 24. http://dx.doi.org/10.3917/afcul.055.0024.
Full text
8
Huang, Lingbo, Yushi Chen, and Xin He. "Spectral-Spatial Mamba for Hyperspectral Image Classification." Remote Sensing 16, no. 13 (2024): 2449. http://dx.doi.org/10.3390/rs16132449.
Full textAbstract:
Recently, transformer has gradually attracted interest for its excellence in modeling the long-range dependencies of spatial-spectral features in HSI. However, transformer has the problem of the quadratic computational complexity due to the self-attention mechanism, which is heavier than other models and thus has limited adoption in HSI processing. Fortunately, the recently emerging state space model-based Mamba shows great computational efficiency while achieving the modeling power of transformers. Therefore, in this paper, we first proposed spectral-spatial Mamba (SS-Mamba) for HSI classification. Specifically, SS-Mamba mainly includes a spectral-spatial token generation module and several stacked spectral-spatial Mamba blocks. Firstly, the token generation module converts any given HSI cube to spatial and spectral tokens as sequences. And then these tokens are sent to stacked spectral-spatial mamba blocks (SS-MB). Each SS-MB includes two basic mamba blocks and a spectral-spatial feature enhancement module. The spatial and spectral tokens are processed separately by the two basic mamba blocks, correspondingly. Moreover, the feature enhancement module modulates spatial and spectral tokens using HSI sample’s center region information. Therefore, the spectral and spatial tokens cooperate with each other and achieve information fusion within each block. The experimental results conducted on widely used HSI datasets reveal that the proposed SS-Mamba requires less processing time compared with transformer. The Mamba-based method thus opens a new window for HSI classification.
9
Chen, Siran, Yuxiao Luo, Yue Ma, Yu Qiao, and Yali Wang. "H-MBA: Hierarchical MamBa Adaptation for Multi-Modal Video Understanding in Autonomous Driving." Proceedings of the AAAI Conference on Artificial Intelligence 39, no. 2 (2025): 2212–20. https://doi.org/10.1609/aaai.v39i2.32220.
Full textAbstract:
With the prevalence of Multimodal Large Language Models(MLLMs), autonomous driving has encountered new opportunities and challenges. In particular, multi-modal video understanding is critical to interactively analyze what will happen in the procedure of autonomous driving. However, videos in such a dynamical scene that often contains complex spatial-temporal movements, which restricts the generalization capacity of the existing MLLMs in this field. To bridge the gap, we propose a novel Hierarchical Mamba Adaptation (H-MBA) framework to fit the complicated motion changes in autonomous driving videos. Specifically, our H-MBA consists of two distinct modules, including Context Mamba (C-Mamba) and Query Mamba (Q-Mamba). First, C-Mamba contains various types of structure state space models, which can effectively capture multi-granularity video context for different temporal resolution. Second, Q-Mamba flexibly transforms the current frame as the learnable query, and attentively select multi-granularity video context into query. Consequently, it can adaptively integrate all the video contexts of multi-scale temporal resolutions to enhance video understanding. Via a plug-and-play paradigm in MLLMs, our H-MBA shows the remarkable performance on multi-modal video tasks in autonomous driving, e.g., for risk object detection, it outperforms the previous SOTA method with 5.5% mIoU improvement.
10
Huang, Wenbo, Jinghui Zhang, Guang Li, et al. "Manta: Enhancing Mamba for Few-Shot Action Recognition of Long Sub-Sequence." Proceedings of the AAAI Conference on Artificial Intelligence 39, no. 4 (2025): 3751–59. https://doi.org/10.1609/aaai.v39i4.32391.
Full textAbstract:
In few-shot action recognition (FSAR), long sub-sequences of video naturally express entire actions more effectively. However, the high computational complexity of mainstream Transformer-based methods limits their application. Recent Mamba demonstrates efficiency in modeling long sequences, but directly applying Mamba to FSAR overlooks the importance of local feature modeling and alignment. Moreover, long sub-sequences within the same class accumulate intra-class variance, which adversely impacts FSAR performance. To solve these challenges, we propose a Matryoshka MAmba and CoNtrasTive LeArning framework (Manta). Firstly, the Matryoshka Mamba introduces multiple Inner Modules to enhance local feature representation, rather than directly modeling global features. An Outer Module captures dependencies of timeline between these local features for implicit temporal alignment. Secondly, a hybrid contrastive learning paradigm, combining both supervised and unsupervised methods, is designed to mitigate the negative effects of intra-class variance accumulation. The Matryoshka Mamba and the hybrid contrastive learning paradigm operate in two parallel branches within Manta, enhancing Mamba for FSAR of long sub-sequence. Manta achieves new state-of-the-art performance on prominent benchmarks, including SSv2, Kinetics, UCF101, and HMDB51. Extensive empirical studies prove that Manta significantly improves FSAR of long sub-sequence from multiple perspectives.
11
Lu, Song, Min Zhang, Yu Huo, Chenhao Wang, Jingwen Wang, and Chenyu Gao. "SSUM: Spatial–Spectral Unified Mamba for Hyperspectral Image Classification." Remote Sensing 16, no. 24 (2024): 4653. https://doi.org/10.3390/rs16244653.
Full textAbstract:
How to effectively extract spectral and spatial information and apply it to hyperspectral image classification (HSIC) has been a hot research topic. In recent years, the transformer-based HSIC models have attracted much interest due to their advantages in long-distance modeling of spatial and spectral features in hyperspectral images (HSIs). However, the transformer-based method suffers from high computational complexity, especially in HSIC tasks that require processing large amounts of data. In addition, the spatial variability inherent in HSIs limits the performance improvement of HSIC. To handle these challenges, a novel Spectral–Spatial Unified Mamba (SSUM) model is proposed, which introduces the State Space Model (SSM) into HSIC tasks to reduce computational complexity and improve model performance. The SSUM model is composed of two branches, i.e., the Spectral Mamba branch and the Spatial Mamba branch, designed to extract the features of HSIs from both spectral and spatial perspectives. Specifically, in the Spectral Mamba branch, a nearest-neighbor spectrum fusion (NSF) strategy is proposed to alleviate the interference caused by the spatial variability (i.e., same object having different spectra). In addition, a novel sub-spectrum scanning (SS) mechanism is proposed, which scans along the sub-spectrum dimension to enhance the model’s perception of subtle spectral details. In the Spatial Mamba branch, a Spatial Mamba (SM) module is designed by combining a 2D Selective Scan Module (SS2D) and Spatial Attention (SA) into a unified network to sufficiently extract the spatial features of HSIs. Finally, the classification results are derived by uniting the output feature of the Spectral Mamba and Spatial Mamba branch, thus improving the comprehensive performance of HSIC. The ablation studies verify the effectiveness of the proposed NSF, SS, and SM. Comparison experiments on four public HSI datasets show the superior of the proposed SSUM.
12
Shao, Yuxuan, and Liwen Xu. "Multimodal Natural Disaster Scene Recognition with Integrated Large Model and Mamba." Applied Sciences 15, no. 3 (2025): 1149. https://doi.org/10.3390/app15031149.
Full textAbstract:
The accurate identification of natural disasters is crucial in ensuring effective post-disaster relief efforts. However, the existing models for disaster classification often incur high costs. To address this, we propose leveraging the most advanced pre-trained large language models, which offer superior generative and multimodal understanding capabilities. Using a question-answering approach, we extract textual descriptions and category prediction probabilities for disaster scenarios, which are then used as input to our proposed Mamba Multimodal Disaster Recognition Network (Mamba-MDRNet). This model integrates a large pre-trained model with the Mamba mechanism, enabling the selection of the most reliable modality information as a robust basis for scene classification. Extensive experiments demonstrate consistent performance improvements across various visual models with heterogeneous architectures. Notably, integrating EfficientNet within Mamba-MDRNet yielded 97.82% accuracy for natural scene classification, surpassing the performance of the CNN (91.75%), ViT (94.50%), and ResNet18 (97.25%). These results highlight the potential of multimodal models combining large models and the Mamba mechanism for disaster type prediction.
13
Tang, Yunxuan, Huaguang Li, Peng Liu, and Tong Li. "Conditional Skipping Mamba Network for Pan-Sharpening." Symmetry 16, no. 12 (2024): 1681. https://doi.org/10.3390/sym16121681.
Full textAbstract:
Pan-sharpening aims to generate high-resolution multispectral (HRMS) images by combining high-resolution panchromatic (PAN) images with low-resolution multispectral (LRMS) data, while maintaining the symmetry of spatial and spectral characteristics. Traditional convolutional neural networks (CNNs) struggle with global dependency modeling due to local receptive fields, and Transformer-based models are computationally expensive. Recent Mamba models offer linear complexity and effective global modeling. However, existing Mamba-based methods lack sensitivity to local feature variations, leading to suboptimal fine-detail preservation. To address this, we propose a Conditional Skipping Mamba Network (CSMN), which enhances global-local feature fusion symmetrically through two modules: (1) the Adaptive Mamba Module (AMM), which improves global perception using adaptive spatial-frequency integration; and (2) the Cross-domain Mamba Module (CDMM), optimizing cross-domain spectral-spatial representation. Experimental results on the IKONOS and WorldView-2 datasets demonstrate that CSMN surpasses existing state-of-the-art methods in achieving superior spectral consistency and preserving spatial details, with performance that is more symmetric in fine-detail preservation.
14
Hu, Jingjing, Dan Guo, Zhan Si, et al. "MOL-Mamba: Enhancing Molecular Representation with Structural & Electronic Insights." Proceedings of the AAAI Conference on Artificial Intelligence 39, no. 1 (2025): 317–25. https://doi.org/10.1609/aaai.v39i1.32009.
Full textAbstract:
Molecular representation learning plays a crucial role in various downstream tasks, such as molecular property prediction and drug design. To accurately represent molecules, Graph Neural Networks (GNNs) and Graph Transformers (GTs) have shown potential in the realm of self-supervised pretraining. However, existing approaches often overlook the relationship between molecular structure and electronic information, as well as the internal semantic reasoning within molecules. This omission of fundamental chemical knowledge in graph semantics leads to incomplete molecular representations, missing the integration of structural and electronic data. To address these issues, we introduce MOL-Mamba, a framework that enhances molecular representation by combining structural and electronic insights. MOL-Mamba consists of an Atom & Fragment Mamba-Graph (MG) for hierarchical structural reasoning and a Mamba-Transformer (MT) fuser for integrating molecular structure and electronic correlation learning. Additionally, we propose a Structural Distribution Collaborative Training and E-semantic Fusion Training framework to further enhance molecular representation learning. Extensive experiments demonstrate that MOL-Mamba outperforms state-of-the-art baselines across eleven chemical-biological molecular datasets.
15
Zhang, Hanwei, Ying Zhu, Dan Wang, et al. "A Survey on Visual Mamba." Applied Sciences 14, no. 13 (2024): 5683. http://dx.doi.org/10.3390/app14135683.
Full textAbstract:
State space models (SSM) with selection mechanisms and hardware-aware architectures, namely Mamba, have recently shown significant potential in long-sequence modeling. Since the complexity of transformers’ self-attention mechanism is quadratic with image size, as well as increasing computational demands, researchers are currently exploring how to adapt Mamba for computer vision tasks. This paper is the first comprehensive survey that aims to provide an in-depth analysis of Mamba models within the domain of computer vision. It begins by exploring the foundational concepts contributing to Mamba’s success, including the SSM framework, selection mechanisms, and hardware-aware design. Then, we review these vision Mamba models by categorizing them into foundational models and those enhanced with techniques including convolution, recurrence, and attention to improve their sophistication. Furthermore, we investigate the widespread applications of Mamba in vision tasks, which include their use as a backbone in various levels of vision processing. This encompasses general visual tasks, medical visual tasks (e.g., 2D/3D segmentation, classification, image registration, etc.), and remote sensing visual tasks. In particular, we introduce general visual tasks from two levels: high/mid-level vision (e.g., object detection, segmentation, video classification, etc.) and low-level vision (e.g., image super-resolution, image restoration, visual generation, etc.). We hope this endeavor will spark additional interest within the community to address current challenges and further apply Mamba models in computer vision.
16
Qin, Mengjie, Yuchao Feng, Zongliang Wu, Yulun Zhang, and Xin Yuan. "Detail Matters: Mamba-Inspired Joint Unfolding Network for Snapshot Spectral Compressive Imaging." Proceedings of the AAAI Conference on Artificial Intelligence 39, no. 6 (2025): 6594–602. https://doi.org/10.1609/aaai.v39i6.32707.
Full textAbstract:
In the coded aperture snapshot spectral imaging system, Deep Unfolding Networks (DUNs) have made impressive progress in recovering 3D hyperspectral images (HSIs) from a single 2D measurement. However, the inherent nonlinear and ill-posed characteristics of HSI reconstruction still pose challenges to existing methods in terms of accuracy and stability. To address this issue, we propose a Mamba-inspired Joint Unfolding Network (MiJUN), which integrates physics-embedded DUNs with learning-based HSI imaging. Firstly, leveraging the concept of trapezoid discretization to expand the representation space of unfolding networks, we introduce an accelerated unfolding network scheme. This approach can be interpreted as a generalized accelerated half-quadratic splitting with a second-order differential equation, which reduces the reliance on initial optimization stages and addresses challenges related to long-range interactions. Crucially, within the Mamba framework, we restructure the Mamba-inspired global-to-local attention mechanism by incorporating a selective state space model and an attention mechanism. This effectively reinterprets Mamba as a variant of the Transformer architecture, improving its adaptability and efficiency. Furthermore, we refine the scanning strategy with Mamba by integrating the tensor mode-k unfolding into the Mamba network. This approach emphasizes the low-rank properties of tensors along various modes, while conveniently facilitating 12 scanning directions. Numerical and visual comparisons on both simulation and real datasets demonstrate the superiority of our proposed MiJUN, and achieving overwhelming detail representation.
17
Arrahman, Arif, Taline D. Kazandjian, Kristina B. M. Still, et al. "A Combined Bioassay and Nanofractionation Approach to Investigate the Anticoagulant Toxins of Mamba and Cobra Venoms and Their Inhibition by Varespladib." Toxins 14, no. 11 (2022): 736. http://dx.doi.org/10.3390/toxins14110736.
Full textAbstract:
Envenomation by elapid snakes primarily results in neurotoxic symptoms and, consequently, are the primary focus of therapeutic research concerning such venoms. However, mounting evidence suggests these venoms can additionally cause coagulopathic symptoms, as demonstrated by some Asian elapids and African spitting cobras. This study sought to investigate the coagulopathic potential of venoms from medically important elapids of the genera Naja (true cobras), Hemachatus (rinkhals), and Dendroaspis (mambas). Crude venoms were bioassayed for coagulant effects using a plasma coagulation assay before RPLC/MS was used to separate and identify venom toxins in parallel with a nanofractionation module. Subsequently, coagulation bioassays were performed on the nanofractionated toxins, along with in-solution tryptic digestion and proteomics analysis. These experiments were then repeated on both crude venoms and on the nanofractionated venom toxins with the addition of either the phospholipase A2 (PLA2) inhibitor varespladib or the snake venom metalloproteinase (SVMP) inhibitor marimastat. Our results demonstrate that various African elapid venoms have an anticoagulant effect, and that this activity is significantly reduced for cobra venoms by the addition of varespladib, though this inhibitor had no effect against anticoagulation caused by mamba venoms. Marimastat showed limited capacity to reduce anticoagulation in elapids, affecting only N. haje and H. haemachatus venom at higher doses. Proteomic analysis of nanofractionated toxins revealed that the anticoagulant toxins in cobra venoms were both acidic and basic PLA2s, while the causative toxins in mamba venoms remain uncertain. This implies that while PLA2 inhibitors such as varespladib and metalloproteinase inhibitors such as marimastat are viable candidates for novel snakebite treatments, they are not likely to be effective against mamba envenomings.
18
Wang, Gui, Yuexiang Li, Wenting Chen, et al. "S³-Mamba: Small-Size-Sensitive Mamba for Lesion Segmentation." Proceedings of the AAAI Conference on Artificial Intelligence 39, no. 7 (2025): 7655–64. https://doi.org/10.1609/aaai.v39i7.32824.
Full textAbstract:
Small lesions play a critical role in early disease diagnosis and intervention of severe infections. Popular models often face challenges in segmenting small lesions, as it occupies only a minor portion of an image, while down-sampling operations may inevitably lose focus on local features of small lesions. To tackle the challenges, we propose a Small-Size-Sensitive Mamba (S³-Mamba), which promotes the sensitivity to small lesions across three dimensions: channel, spatial, and training strategy. Specifically, an Enhanced Visual State Space block is designed to focus on small lesions through multiple residual connections to preserve local features, and selectively amplify important details while suppressing irrelevant ones through channel-wise attention. A Tensor-based Cross-feature Multi-scale Attention is designed to integrate input image features and intermediate-layer features with edge features and exploit the attentive support of features across multiple scales, thereby retaining spatial details of small lesions at various granularities. Finally, we introduce a novel regularized curriculum learning to automatically assess lesion size and sample difficulty, and gradually focus from easy samples to hard ones like small lesions. Extensive experiments on three medical image segmentation datasets show the superiority of our S³-Mamba, especially in segmenting small lesions.
19
Xu, Jian, Liangbing Chen, Wenqian Xu, Longxuan Dai, Chenxi Wang, and Lei Hu. "ET-Mamba: A Mamba Model for Encrypted Traffic Classification." Information 16, no. 4 (2025): 314. https://doi.org/10.3390/info16040314.
Full textAbstract:
With the widespread use of encryption protocols on network data, fast and effective encryption traffic classification can improve the efficiency of traffic analysis. A resampling method combining Wasserstein GAN and random selection is proposed for solving the dataset imbalance problem, and it uses Wasserstein GAN for oversampling and random selection for undersampling to achieve class equalization. Based on Mamba, an ultra-low parametric quantity model, we propose an encrypted traffic classification model, ET-Mamba, which has a pre-training phase and a fine-tuning phase. During the pre-training phase, positional embedding is used to characterize the blocks of the traffic grayscale image, and random masking is used to strengthen the learning of the intrinsic correlation among the blocks of the traffic grayscale image. During the fine-tuning phase, the agent attention mechanism is adopted in the feature extraction phase to achieve global information modeling at a low computational cost, and the SmoothLoss function is designed to solve the problem of the insufficient generalization ability of cross-entropy loss function during training. The experimental results show that the proposed model significantly reduces the number of parameters and outperforms other models in terms of classification accuracy on non-VPN datasets.
20
Zhang, Tao, Haobo Yuan, Lu Qi, et al. "Point Cloud Mamba: Point Cloud Learning via State Space Model." Proceedings of the AAAI Conference on Artificial Intelligence 39, no. 10 (2025): 10121–30. https://doi.org/10.1609/aaai.v39i10.33098.
Full textAbstract:
Recently, state space models have exhibited strong global modeling capabilities and linear computational complexity in contrast to transformers. This research focuses on applying such architecture to more efficiently and effectively model point cloud data globally with linear computational complexity. In particular, for the first time, we demonstrate that Mamba-based point cloud methods can outperform previous methods based on transformer or multi-layer perceptrons (MLPs). To enable Mamba to process 3-D point cloud data more effectively, we propose a novel Consistent Traverse Serialization method to convert point clouds into 1-D point sequences while ensuring that neighboring points in the sequence are also spatially adjacent. Consistent Traverse Serialization yields six variants by permuting the order of x, y, and z coordinates, and the synergistic use of these variants aids Mamba in comprehensively observing point cloud data. Furthermore, to assist Mamba in handling point sequences with different orders more effectively, we introduce point prompts to inform Mamba of the sequence’s arrangement rules. Finally, we propose positional encoding based on spatial coordinate mapping to inject positional information into point cloud sequences more effectively. Point Cloud Mamba surpasses the state-of-the-art (SOTA) point-based method PointNeXt and achieves new SOTA performance on the ScanObjectNN, ModelNet40, ShapeNetPart, and S3DIS datasets. It is worth mentioning that when using a more powerful local feature extraction module, our PCM achieves 79.6 mIoU on S3DIS, significantly surpassing the previous SOTA models, DeLA and PTv3, by 5.5 mIoU and 4.9 mIoU, respectively.
21
Liu, Jie, Deyuan Li, and Xin Xu. "Enhancing bridge damage detection with Mamba-Enhanced HRNet for semantic segmentation." PLOS ONE 19, no. 10 (2024): e0312136. http://dx.doi.org/10.1371/journal.pone.0312136.
Full textAbstract:
With the acceleration of urbanization, bridges, as crucial infrastructure, their structural health and stability are paramount to public safety. This paper proposes Mamba-Enhanced HRNet for bridge damage detection. Mamba-Enhanced HRNet integrates the advantages of HRNet’s multi-resolution parallel design and VMamba’s visual state space model. By replacing the residual convolutional blocks in HRNet with a combination of VSS blocks and convolution, this model enhances the network’s capability to capture global contextual information while maintaining computational efficiency. This work builds an extensive dataset with multiple damage kinds and uses Mean Intersection over Union (Mean IoU) as the assessment metric to assess the performance of Mamba-Enhanced HRNet. Experimental results demonstrate that Mamba-Enhanced HRNet achieves significant performance improvements in bridge damage semantic segmentation tasks, with Mean IoU scores of 0.963, outperforming several other semantic segmentation models.
22
Battezzati, Agustina. "¿Generaciones de artistas? O cómo configurar una escena del arte." Index, revista de arte contemporáneo, no. 07 (June 30, 2019): 12–19. http://dx.doi.org/10.26807/cav.v0i07.225.
Full textAbstract:
Las generaciones son categorías socialmente construidas que permiten delimitar y definir prácticas artísticas. Cuando este concepto es utilizado en la discursividad por agentes hegemónicos del campo artístico, es posible evidenciar parámetros de valor del arte que se intentan instituir como legítimos. Este artículo estudia el uso operativo del concepto de ‘generación’ en la discursividad producida y difundida por el Museo de Arte Moderno de Buenos Aires (Mamba) y el Museo de Arte Latinoamericano de Buenos Aires (Malba) con el objetivo de trazar los lineamientos propuestos en torno a la escena artística argentina del comienzo del siglo XXI.
23
Sun, Mengyuan, Liejun Wang, Shaochen Jiang, Shuli Cheng, and Lihan Tang. "HyperSMamba: A Lightweight Mamba for Efficient Hyperspectral Image Classification." Remote Sensing 17, no. 12 (2025): 2008. https://doi.org/10.3390/rs17122008.
Full textAbstract:
Deep learning has recently achieved remarkable progress in hyperspectral image (HSI) classification. Among these advancements, the Transformer-based models have gained considerable attention due to their ability to establish long-range dependencies. However, the quadratic computational complexity of the self-attention mechanism limits its application in hyperspectral image classification (HSIC). Recently, the Mamba architecture has shown outstanding performance in 1D sequence modeling tasks owing to its lightweight linear sequence operations and efficient parallel scanning capabilities. Nevertheless, its application in HSI classification still faces challenges. Most existing Mamba-based approaches adopt various selective scanning strategies for HSI serialization, ensuring the adjacency of scanning sequences to enhance spatial continuity. However, these methods lead to substantially increased computational overhead. To overcome these challenges, this study proposes the Hyperspectral Spatial Mamba (HyperSMamba) model for HSIC, aiming to reduce computational complexity while improving classification performance. The suggested framework consists of the following key components: (1) a Multi-Scale Spatial Mamba (MS-Mamba) encoder, which refines the state-space model (SSM) computation by incorporating a Multi-Scale State Fusion Module (MSFM) after the state transition equations of original SSMs. This module aggregates adjacent state representations to reinforce spatial dependencies among local features; (2) our proposed Adaptive Fusion Attention Module (AFAttention) to dynamically fuse bidirectional Mamba outputs for optimizing feature representation. Experiments were performed on three HSI datasets, and the findings demonstrate that HyperSMamba attains overall accuracy of 94.86%, 97.72%, and 97.38% on the Indian Pines, Pavia University, and Salinas datasets, while maintaining low computational complexity. These results confirm the model’s effectiveness and potential for practical application in HSIC tasks.
24
He, Xilin, Haijian Liang, Boyi Peng, et al. "MSAmba: Exploring Multimodal Sentiment Analysis with State Space Models." Proceedings of the AAAI Conference on Artificial Intelligence 39, no. 2 (2025): 1309–17. https://doi.org/10.1609/aaai.v39i2.32120.
Full textAbstract:
Multimodal sentiment analysis, which learns a model to process multiple modalities simultaneously and predict a sentiment value, is an important area of affective computing. Modeling sequential intra-modal information and enhancing cross-modal interactions are crucial to multimodal sentiment analysis. In this paper, we propose MSAmba, a novel hybrid Mamba-based architecture for multimodal sentiment analysis, consisting of two core blocks: Intra-Modal Sequential Mamba (ISM) block and Cross-Modal Hybrid Mamba (CHM) block, to comprehensively address the above-mentioned challenges with hybrid state space models. Firstly, the ISM block models the sequential information within each modality in a bi-directional manner with the assistance of global information. Subsequently, the CHM blocks explicitly model centralized cross-modal interaction with a hybrid combination of Mamba and attention mechanism to facilitate information fusion across modalities. Finally, joint learning of the intra-modal tokens and cross-modal tokens is utilized to predict the sentiment values. This paper serves as one of the pioneering works to unravel the outstanding performances and great research potential of Mamba-based methods in the task of multimodal sentiment analysis. Experiments on CMU-MOSI, CMU-MOSEI and CH-SIMS demonstrate the superior performance of the proposed MSAmba over prior Transformer-based and CNN-based methods.
25
Blumenthal, Ryan, Pieter Evelyn Pienaar Scholtz, and Jenna-lee Shuttleworth. "Black Mamba Death." American Journal of Forensic Medicine and Pathology 40, no. 4 (2019): 356–60. http://dx.doi.org/10.1097/paf.0000000000000496.
Full text
26
Hu, Yishan, Jun Zhao, Chen Qi, Yan Qiang, Juanjuan Zhao, and Bo Pei. "VC-Mamba: Causal Mamba representation consistency for video implicit understanding." Knowledge-Based Systems 317 (May 2025): 113437. https://doi.org/10.1016/j.knosys.2025.113437.
Full text
27
Dai, Tongyang, Huiyu Xiang, Chongjie Leng, Song Huang, Guanghui He, and Shishuo Han. "LDMNet: Enhancing the Segmentation Capabilities of Unmanned Surface Vehicles in Complex Waterway Scenarios." Applied Sciences 14, no. 17 (2024): 7706. http://dx.doi.org/10.3390/app14177706.
Full textAbstract:
Semantic segmentation-based Complex Waterway Scene Understanding has shown great promise in the environmental perception of Unmanned Surface Vehicles. Existing methods struggle with estimating the edges of obstacles under conditions of blurred water surfaces. To address this, we propose the Lightweight Dual-branch Mamba Network (LDMNet), which includes a CNN-based Deep Dual-branch Network for extracting image features and a Mamba-based fusion module for aggregating and integrating global information. Specifically, we improve the Deep Dual-branch Network structure by incorporating multiple Atrous branches for local fusion; we design a Convolution-based Recombine Attention Module, which serves as the gate activation condition for Mamba-2 to enhance feature interaction and global information fusion from both spatial and channel dimensions. Moreover, to tackle the directional sensitivity of image serialization and the impact of the State Space Model’s forgetting strategy on non-causal data modeling, we introduce a Hilbert curve scanning mechanism to achieve multi-scale feature serialization. By stacking feature sequences, we alleviate the local bias of Mamba-2 towards image sequence data. LDMNet integrates the Deep Dual-branch Network, Recombine Attention, and Mamba-2 blocks, effectively capturing the long-range dependencies and multi-scale global context information of Complex Waterway Scene images. The experimental results on four benchmarks show that the proposed LDMNet significantly improves obstacle edge segmentation performance and outperforms existing methods across various performance metrics.
28
He, Sicheng, Junzhong Ji, and Minglong Lei. "Decomposed Spatio-Temporal Mamba for Long-Term Traffic Prediction." Proceedings of the AAAI Conference on Artificial Intelligence 39, no. 11 (2025): 11772–80. https://doi.org/10.1609/aaai.v39i11.33281.
Full textAbstract:
Traffic prediction provides vital support for urban traffic management and has received extensive research interest. By virtue of the ability to effectively learn spatial and temporal dependencies from a global view, Transformers have achieved superior performance in long-term traffic prediction. However, existing methods usually underrate the complex spatio-temporal entanglement in long-range sequences. Compared with purely temporal entanglement, spatio-temporal data emphasizes the entangled dynamics under the restrictions of traffic networks, which brings additional difficulties. Moreover, the computational costs of spatio-temporal Transformers scale quadratically as the sequence length grows, limiting their applications on long-range and large-scale scenarios. To address these problems, we propose a decomposed spatio-temporal Mamba (DST-Mamba) for traffic prediction. We aim to apply temporal decomposition to the entangled sequences and obtain the seasonal and trend parts. Shifting from the temporal view to the spatial view, we leverage Mamba, a state space model with near-linear complexity, to capture seasonal variations in a node-centric manner. Meanwhile, multi-scale trend information is extracted and aggregated by simple linear layers. Such combination equips DST-Mamba with superior capability to model long-range spatio-temporal dependencies while remaining efficient compared with Transformers. Experimental results across five real-world datasets demonstrate that DST-Mamba can capture both local fluctuations and global trends within traffic patterns, achieving state-of-the-art performance with favorable efficiency.
29
Liu, Ziwei, Qidong Liu, Yejing Wang, et al. "SIGMA: Selective Gated Mamba for Sequential Recommendation." Proceedings of the AAAI Conference on Artificial Intelligence 39, no. 12 (2025): 12264–72. https://doi.org/10.1609/aaai.v39i12.33336.
Full textAbstract:
Sequential Recommender Systems (SRS) has stood out as a highly promising technique in numerous domains due to its impressive capability of capturing complex user preferences. Current SRS have employed transformer-based models to give the next-item prediction. Nevertheless, its quadratic computational complexity has often resulted in notable inefficiencies, posing a significant obstacle to real-time recommendation processes. Recently, Mamba has demonstrated its exceptional effectiveness in time series prediction, delivering substantial improvements in both efficiency and effectiveness. However, directly applying Mamba to SRS poses certain challenges. Its unidirectional structure may impede the ability to capture contextual information in user-item interactions, while its instability in state estimation may hinder the ability to capture short-term patterns in interaction sequences. To address these issues, we propose a novel framework called Selective Gated Mamba for Sequential Recommendation (SIGMA). By introducing the Partially Flipped Mamba (PF-Mamba), we construct a special bi-directional structure to address the context modeling challenge. Then, to consolidate PF-Mamba's performance, we employed an input-dependent Dense Selective Gate (DS Gate) to allocate the weights of the two directions and further filter the sequential information. Moreover, for short sequence modeling, we devise a Feature Extract GRU (FE-GRU) to capture the short-term dependencies. Experimental results demonstrate that SIGMA significantly outperforms existing baselines across five real-world datasets. Our implementation code is available in Supplementary Material to ease reproducibility.
30
Agatha, Febriana, and Septia Winduwati. "Persepsi Perempuan Muda terhadap Komunikasi Nonverbal Artifaktual pada Fenomena Fashion Style Cewek Mamba, Bumi, dan Kue." Kiwari 2, no. 2 (2023): 257–62. http://dx.doi.org/10.24912/ki.v2i2.24009.
Full textAbstract:
Fashion is an inseparable part of everyday life. Nowadays, fashion is not only how we dress or look but also a medium for communication which can represent human expression and self-image. This research aims to find out young women's perceptions of artifactual non-verbal communication, especially in the phenomenon of fashion style cewek mamba, cewek bumi and cewek kue. The communication theory used is artifactual non-verbal communication which includes fashion. In this study, used a descriptive qualitative research approach with a case study method. Based on the analysis conducted with the informants, it can be concluded that the informants' perceptions related to the phenomenon of fashion style cewek mamba, cewek bumi and cewek kue are different. The informants stated that the phenomenon of fashion style of cewek mamba, cewek bumi and cewek kue does not represent the original personality of the individual but is merely a fashion expression that shows the mood and the heart of the individual. Fashion merupakan bagian yang tidak dapat dilepaskan dalam kehidupan sehari-hari. Saat ini fashion tidak hanya bagaimana kita berbusana atau berpenampilan saja melainkan menjadi medium untuk berkomunikasi dimana dapat menampilkan ekspresi dan citra diri manusia. Penelitian ini bertujuan untuk mengetahui persepsi perempuan muda terhadap komunikasi non-verbal artifaktual khususnya pada fenomena fashion style cewek mamba, cewek bumi dan cewek kue. Teori komunikasi yang digunakan adalah komunikasi non-verbal artifaktual yang didalamnya mencakup fashion. Dalam penelitian ini, peneliti menggunakan pendekatan penelitian kualitatif deskriptif dengan metode studi kasus. Berdasarkan analisis yang dilakukan dengan para informan dapat disimpulkan bahwa persepsi para informan terkait dengan fenomena fashion style cewek mamba, cewek bumi dan cewek kue berbeda-beda. Para informan menyatakan fenomena fashion style cewek mamba, cewek bumi dan cewek kue tidak mewakili kepribadian asli individu melainkan merupakan ekspresi fashion semata yang menunjukkan mood dan suasana hati pemakai.
31
Suo, Yongfeng, Zhengnian Ding, and Tao Zhang. "The Mamba Model: A Novel Approach for Predicting Ship Trajectories." Journal of Marine Science and Engineering 12, no. 8 (2024): 1321. http://dx.doi.org/10.3390/jmse12081321.
Full textAbstract:
To address the complexity of ship trajectory prediction, this study explored the efficacy of the Mamba model, a relatively new deep-learning framework. In order to evaluate the performance of the Mamba model relative to traditional models, which often struggle to cope with the dynamic and nonlinear nature of maritime navigation data, we analyzed a dataset consisting of intricate ship trajectory data. The prediction accuracy and inference speed of the model were evaluated using metrics such as the mean absolute error (MAE) and root mean square error (RMSE). The Mamba model not only excelled in terms of the computational efficiency, with inference times of 0.1759 s per batch—approximately 7.84 times faster than the widely used Transformer model—it also processed 3.9052 samples per second, which is higher than the Transformer model’s 0.7246 samples per second. Additionally, it demonstrated high prediction accuracy and the lowest loss among the evaluated models. The Mamba model provides a new tool for ship trajectory prediction, which represents an advancement in addressing the challenges of maritime trajectory analysis when compared to existing deep-learning methods.
32
Zhang, Xinyi, Qiqi Bao, Qinpeng Cui, Wenming Yang, and Qingmin Liao. "Pose Magic: Efficient and Temporally Consistent Human Pose Estimation with a Hybrid Mamba-GCN Network." Proceedings of the AAAI Conference on Artificial Intelligence 39, no. 10 (2025): 10248–56. https://doi.org/10.1609/aaai.v39i10.33112.
Full textAbstract:
Current state-of-the-art (SOTA) methods in 3D Human Pose Estimation (HPE) are primarily based on Transformers. However, existing Transformer-based 3D HPE backbones often encounter a trade-off between accuracy and computational efficiency. To resolve the above dilemma, in this work, we leverage recent advances in state space models and utilize Mamba for high-quality and efficient long-range modeling. Nonetheless, Mamba still faces challenges in precisely exploiting local dependencies between joints. To address these issues, we propose a new attention-free hybrid spatiotemporal architecture named Hybrid Mamba-GCN (Pose Magic). This architecture introduces local enhancement with GCN by capturing relationships between neighboring joints, thus producing new representations to complement Mamba's outputs. By adaptively fusing representations from Mamba and GCN, Pose Magic demonstrates superior capability in learning the underlying 3D structure. To meet the requirements of real-time inference, we also provide a fully causal version. Extensive experiments show that Pose Magic achieves new SOTA results (0.9 mm drop) while saving 74.1% FLOPs. In addition, Pose Magic exhibits optimal motion consistency and the ability to generalize to unseen sequence lengths.
33
Xu, Ziang, and Xin Chen. "Natural gas pipeline leak detection method based on 1D CNN-Mamba integrated acoustic signal classification." Journal of Physics: Conference Series 3011, no. 1 (2025): 012067. https://doi.org/10.1088/1742-6596/3011/1/012067.
Full textAbstract:
Abstract The transportation of natural gas requires the construction of complex pipeline systems. However, as the pipelines age, damage and leakage incidents occur frequently, making pipeline leak detection particularly critical. This paper proposes an acoustic signal classification method integrated with an improved 1D CNN-Mamba model for pipeline leak detection. The method combines the 1D-CNN and Mamba modules, training them separately before jointly fine-tuning, significantly improving detection accuracy. By utilizing depthwise separable convolutions, the model parameters are reduced, and the computational cost is lowered with the Mamba block. Experimental results demonstrate that the proposed method offers a significant performance improvement, with an average accuracy of 93.24%, a 0.74% increase compared to the PNN in 12 classifications.
34
Bai, Cong, Zhonghao Lin, Jinglin Zhang, and Shengyong Chen. "Dust-Mamba: An Efficient Dust Storm Detection Network with Multiple Data Sources." Proceedings of the AAAI Conference on Artificial Intelligence 39, no. 27 (2025): 27813–21. https://doi.org/10.1609/aaai.v39i27.34997.
Full textAbstract:
Accurate detection of dust storms is challenging due to complex meteorological interactions. With the development of deep learning, deep neural networks have been increasingly applied to dust storm detection, offering better learning and generalization capabilities compared to traditional physical modeling. However, existing methods face some limitations, leading to performance bottlenecks in dust storm detection. From the task perspective, existing research focuses on occurrence detection while neglecting intensity detection. From the data perspective, existing research fails to explore the utilization of multi-source data. From the model perspective, most models are built on convolutional neural networks, which have an inherent limitation in capturing long-range dependencies. To address the challenges mentioned, this study proposes Dust-Mamba. To the best of our knowledge, this study is the first attempt to accomplish both the occurrence and intensity detection of dust storms with advanced deep learning technology. In Dust-Mamba, multi-source data is introduced to provide a comprehensive perspective, Mamba and attention are applied to boost feature selection while maintaining long-range modeling capability. Additionally, this study proposes Structure Sharing Transfer Learning Strategies for intensity detection, which further enhances the performance of Dust-Mamba with minimal time cost. As shown by experiments, Dust-Mamba achieves Dice scores of 0.963 for occurrence detection and 0.560 for intensity detection, surpassing several baseline models. In conclusion, this study offers valuable baselines for dust storm detection, with significant reference value and promising application potential.
35
Xu, Wei, Yi Wan, Dong Zhao, and Long Zhang. "Efficient Mamba: Overcoming the visual limitations of Mamba with innovative structures." Image and Vision Computing 161 (September 2025): 105569. https://doi.org/10.1016/j.imavis.2025.105569.
Full text
36
Li, Xueyang, Yunzhong Lou, Yu Song, and Xiangdong Zhou. "Mamba-CAD: State Space Model for 3D Computer-Aided Design Generative Modeling." Proceedings of the AAAI Conference on Artificial Intelligence 39, no. 5 (2025): 5013–21. https://doi.org/10.1609/aaai.v39i5.32531.
Full textAbstract:
Computer-Aided Design (CAD) generative modeling has a strong and long-term application in the industry. Recently, the parametric CAD sequence as the design logic of an object has been widely mined by sequence models. However, the industrial CAD models, especially in component objects, are fine-grained and complex, requiring a longer parametric CAD sequence to define. To address the problem, we introduce Mamba-CAD, a self-supervised generative modeling for complex CAD models in the industry, which can model on a longer parametric CAD sequence. Specifically, we first design an encoder-decoder framework based on a Mamba architecture and pair it with a CAD reconstruction task for pre-training to model the latent representation of CAD models; and then we utilize the learned representation to guide a generative adversarial network to produce the fake representation of CAD models, which would be finally recovered into parametric CAD sequences via the decoder of Mamba-CAD. To train Mamba-CAD, we further create a new dataset consisting of 77,078 CAD models with longer parametric CAD sequences. Comprehensive experiments are conducted to demonstrate the effectiveness of our model under various evaluation metrics, especially in the generation length of valid parametric CAD sequences.
37
Zhang, Junyi, Renwen Chen, Fei Liu, Hao Liu, Boyu Zheng, and Chenyu Hu. "DC-Mamba: A Novel Network for Enhanced Remote Sensing Change Detection in Difficult Cases." Remote Sensing 16, no. 22 (2024): 4186. http://dx.doi.org/10.3390/rs16224186.
Full textAbstract:
Remote sensing change detection (RSCD) aims to utilize paired temporal remote sensing images to detect surface changes in the same area. Traditional CNN-based methods are limited by the size of the receptive field, making it difficult to capture the global features of remote sensing images. In contrast, Transformer-based methods address this issue with their powerful modeling capabilities. However, applying the Transformer architecture to image processing introduces a quadratic complexity problem, significantly increasing computational costs. Recently, the Mamba architecture based on state-space models has gained widespread application in the field of RSCD due to its excellent global feature extraction capabilities and linear complexity characteristics. Nevertheless, existing Mamba-based methods lack optimization for complex change areas, making it easy to lose shallow features or local features, which leads to poor performance on challenging detection cases and high-difficulty datasets. In this paper, we propose a Mamba-based RSCD network for difficult cases (DC-Mamba), which effectively improves the model’s detection capability in complex change areas. Specifically, we introduce the edge-feature enhancement (EFE) block and the dual-flow state-space (DFSS) block, which enhance the details of change edges and local features while maintaining the model’s global feature extraction capability. We propose a dynamic loss function to address the issue of sample imbalance, giving more attention to difficult samples during training. Extensive experiments on three change detection datasets demonstrate that our proposed DC-Mamba outperforms existing state-of-the-art methods overall and exhibits significant performance improvements in detecting difficult cases.
38
Mutmainah, Siti, Muhammad Muatho' bil Khafi, Musfirotun Naimah, Marisa Diana Sakhiro Layali, and Nurul Aini. "PEMANFAATAN DAUR ULANG SAMPAH ANORGANIK DALAM MENINGKATKAN KREATIFITAS SANTRI." Pandalungan: Jurnal Pengabdian kepada Masyarakat 3, no. 1 (2024): 24–30. https://doi.org/10.62097/pandalungan.v3i1.998.
Full textAbstract:
Peneliti berinovasi untuk melakukan kegiatan pengelolaan dan pengolahan sampah di pondok pesantren Mamba`ul khoiriyatil islamiyyah dengan membentuk langkah kreatif untuk sampah yang Anorganik guna untuk mengurangi jumlah sampah yang harus dibuang ke Tempat Pembuangan Sampah (TPS) dan meningkatkan kebersihan lingkungan pesantren, meningkatkan kesehatan, dan pencemaran dapat diminimalisir. Dari penjelasan yang diuraikan diatas maka permasalahan yang peneliti Rumuskan adalah: 1) Bagaimana cara mengatasi daur ulang sampah Anorganik di pesantren Mamba`ul Khoiriyatil Islamiyyah Bangsalsari-Jember 2) Bagaimana pemanfaatan sampah Anorganik di pesantren Mamba`ul Khoiriyatil Islamiyyah Bangsalsari-Jember Adapun metode yang digunakan dalam progam pendaur ulangan sampah Anorganik dalam meningkatkan kreatifitas santri di pesantren Mamba`ul Khoiriyatil Islamiyyah Bangsalsari-Jember ini terbagi menjadi 2 tahap yaitu penyuluhan dan pelatihan 1. Mengadakan penyuluhan (sosialisasi) cara pengelolaan sampah plastik bagi santri. Dengan memberikan penyuluhan atau sosialisasi tentang pengolahan sampah Anorganik yang selanjutnya bisa diolah menjadi barang bermanfaat. 2. Pelaksanan Kegiatan pelatihan a. Tahap Persiapan b. Tahap Pelaksanaan, Pelaksanaan kegiatan pelatihan sekaligus pengabdian kepada masyarakat mengenai pemanfaatan sampah plastic menjadi kerajinan tangan berhasil dilakukan. Para santri sudah memahami tata cara memanfaatkan sampah plastik Strategi pengelolaan sampah yang dilakukan dengan baik mampu meningkatkan pendidikan karakter peduli lingkungan melalui kegiatan pengumpulan sampah anorganik di Pondok pesantren Mamba`ul Khoiriyatil Islamiyyah, Pelaksanaan kegiatan pelatihan sekaligus pengabdian kepada masyarakat mengenai pemanfaatan sampah plastic menjadi kerajinan tangan berhasil dilakukan. Para santri sudah memahami tata cara memanfaatkan sampah plastik sehingga dapat dihasilkan berbagai macam hasil kreasi dari sampah plastik seperti tas, bros, tempat barang-barang kecil dan berbagai karya seni lainnya yang mungkin dapat dimanfaatkan. Kebersihan lingkungan di sekitar pesantren dapat terjaga
39
Alhudhaif, Adi, and Kemal Polat. "Non-invasive enhanced hypertension detection through ballistocardiograph signals with Mamba model." PeerJ Computer Science 11 (February 21, 2025): e2711. https://doi.org/10.7717/peerj-cs.2711.
Full textAbstract:
This study explores using ballistocardiography (BCG), a non-invasive cardiovascular monitoring technique, combined with advanced machine learning and deep learning models for hypertension detection. The motivation behind this research is to develop a non-invasive and efficient approach for long-term hypertension monitoring, facilitating home-based health assessments. A dataset of 128 BCG recordings has been used, capturing body micro-vibrations from cardiac activity. Various classification models, including Mamba Classifier, Transformer, Stacking, Voting, and XGBoost, were applied to differentiate hypertensive individuals from normotensive ones. In this study, integrating BCG signals with deep learning and machine learning models for hypertension detection is distinguished from previous literature by employing the Mamba deep learning architecture and Transformer-based models. Unlike conventional methods in literature, this study enables more effective analysis of time-series data with the Mamba architecture, capturing long-term signal dependencies and achieving higher accuracy rates. In particular, the combined use of Mamba architecture and the Transformer model’s signal processing capabilities represents a novel approach not previously seen in the literature. While existing studies on BCG signals typically rely on traditional machine learning algorithms, this study aims to achieve higher success rates in hypertension detection by integrating signal processing and deep learning stages. The Mamba Classifier outperformed other models, achieving an accuracy of 95.14% and an AUC of 0.9922 in the 25% hold-out validation. Transformer and Stacking models also demonstrated strong performance, while the Voting and XGBoost models showed comparatively lower results. When combined with artificial intelligence techniques, the findings indicate the potential of BCG signals in providing non-invasive, long-term hypertension detection. The results suggest that the Mamba Classifier is the most effective model for this dataset. This research underscores the potential of BCG technology for continuous home-based health monitoring, providing a feasible alternative to traditional methods. Future research should aim to validate these findings with larger datasets and explore the clinical applications of BCG for cardiovascular disease monitoring.
40
Li, Yao. "Semantic Web-Based Prediction Method for Goodwill Impairment in Listed Companies Using Mamba." International Journal on Semantic Web and Information Systems 20, no. 1 (2024): 1–31. http://dx.doi.org/10.4018/ijswis.356492.
Full textAbstract:
In the context of globalization and intense market competition, mergers and acquisitions (M&A) have become a common strategy for enterprises to expand and transform. However, goodwill issues in M&A are increasingly concerning. Traditional goodwill impairment prediction models face drawbacks like reliance on precise predictions, large datasets, complexity, poor interpretability, high computational costs, and data acquisition difficulties. This paper proposes a prediction model based on an improved Mamba algorithm. By processing financial data from listed companies in the CSMAR database, the model constructs lagged and rolling statistical features to reflect performance trends. The Mamba algorithm dynamically adjusts input parameters through a Selective State-Space Model (SSM), capturing dependencies in long-sequence data and improving prediction accuracy and timeliness. Experimental results show the Mamba algorithm excels in handling long-sequence data, offering valuable guidance for financial management and risk control.
41
Liu, Wenting, Xinming Lu, Jianxin Zhang, Dan Li, and Xingli Zhang. "MOU-Mamba: Multi-Order U-shape Mamba for infrared small target detection." Optics & Laser Technology 187 (September 2025): 112851. https://doi.org/10.1016/j.optlastec.2025.112851.
Full text
42
Huang, Jiahui, Lei Liu, Hongwei Zhao, Tianqi Li, and Bin Li. "RUL-Mamba: Mamba-based remaining useful life prediction for lithium-ion batteries." Journal of Energy Storage 120 (June 2025): 116376. https://doi.org/10.1016/j.est.2025.116376.
Full text
43
Yao, Mufeng, Jinlong Peng, Qingdong He, et al. "MM-Tracker: Motion Mamba for UAV-platform Multiple Object Tracking." Proceedings of the AAAI Conference on Artificial Intelligence 39, no. 9 (2025): 9409–17. https://doi.org/10.1609/aaai.v39i9.33019.
Full textAbstract:
Multiple object tracking (MOT) from unmanned aerial vehicle (UAV) platforms requires efficient motion modeling. This is because UAV-MOT faces both local object motion and global camera motion. Motion blur also increases the difficulty of detecting large moving objects. Previous UAV motion modeling approaches either focus only on local motion or ignore motion blurring effects, thus limiting their tracking performance and speed. To address these issues, we propose the Motion Mamba Module, which explores both local and global motion features through cross-correlation and bi-directional Mamba Modules for better motion modeling. To address the detection difficulties caused by motion blur, we also design motion margin loss to effectively improve the detection accuracy of motion blurred objects. Based on the Motion Mamba module and motion margin loss, our proposed MM-Tracker surpasses the state-of-the-art in two widely open-source UAV-MOT datasets.
44
Li, Chade, Pengju Zhang, Bo Liu, Hao Wei, and Yihong Wu. "FEAST-Mamba: FEAture and SpaTial Aware Mamba Network with Bidirectional Orthogonal Fusion for Cross-Modal Point Cloud Segmentation." Proceedings of the AAAI Conference on Artificial Intelligence 39, no. 5 (2025): 4634–42. https://doi.org/10.1609/aaai.v39i5.32489.
Full textAbstract:
Point cloud segmentation has a wide range of applications in autonomous driving, augmented reality and virtual reality. Multi-modal fusion strategies have received increasing attention in point cloud segmentation recently. Despite the success, existing methods usually generate unnecessary information loss or redundancy. In this paper, we propose FEAST-Mamba, a novel FEAture and SpaTial aware Mamba network to tackle multi-modal point cloud segmentation. To exploit the complementarity between different modals, we propose a bidirectional orthogonal attention module, where features are first bidirectionally interacted with each other through cross-modal attention, and then orthogonal fusion is used to reduce feature redundancy. Furthermore, a reordering strategy is proposed for the Mamba architecture that takes into account both spatial and semantic information during cross-modal feature ordering. Experiments on indoor datasets, S3DIS and ScanNet, and outdoor datasets, nuScenes and SemanticKITTI, show that the proposed method achieves state-of-the-art performances.
45
Vinayak Ashok Bharadi. "Deep Mamba Siamese Network with Feedforward Layers for Robust Online Signature Verification." Journal of Information Systems Engineering and Management 10, no. 33s (2025): 1080–87. https://doi.org/10.52783/jisem.v10i33s.5836.
Full textAbstract:
In the realm of digital biometric authentication techniques, online signature verification hold promise as an alternative to traditional offline methods. But due to the nature of data and intraclass variability, online signature verification remains to a difficult task. Sequential models either lack the ability to fit the data (LSTMs) or are computationally very expensive (Transformers). To address this gap, this paper addresses a deep Siamese Neural Network that users Mamba SSM as the backbone connected to feed forward layers for 1v1 Signature verification. Mamba SSM is a recent development in State Space Model architectures that scales linearly with sequence length while giving performance comparable to transformers. Due to use of the Mamba backbone the model proves to be a fast, lightweight, while still accurate method of online signature verification. Our implementation gave an accuracy 0f 80.5% on a 20% test set of the MCYT100 dataset.
46
Li, Sai, and Shuo Huang. "AFA–Mamba: Adaptive Feature Alignment with Global–Local Mamba for Hyperspectral and LiDAR Data Classification." Remote Sensing 16, no. 21 (2024): 4050. http://dx.doi.org/10.3390/rs16214050.
Full textAbstract:
The joint classification of hyperspectral imagery (HSI) and LiDAR data is an important task in the field of remote sensing image interpretation. Traditional classification methods, such as support vector machine (SVM) and random forest (RF), have difficulty capturing the complex spectral–spatial–elevation correlation information. Recently, important progress has been made in HSI-LiDAR classification using Convolutional Neural Networks (CNNs) and Transformers. However, due to the large spatial extent of remote sensing images, the vanilla Transformer and CNNs struggle to effectively capture global context. Moreover, the weak misalignment between multi-source data poses challenges for their effective fusion. In this paper, we introduce AFA–Mamba, an Adaptive Feature Alignment Network with a Global–Local Mamba design that achieves accurate land cover classification. It contains two main core designs: (1) We first propose a Global–Local Mamba encoder, which effectively models context through a 2D selective scanning mechanism while introducing local bias to enhance the spatial features of local objects. (2) We also propose an SSE Adaptive Alignment and Fusion (A2F) module to adaptively adjust the relative positions between multi-source features. This module establishes a guided subspace to accurately estimate feature-level offsets, enabling optimal fusion. As a result, our AFA–Mamba consistently outperforms state-of-the-art multi-source fusion classification approaches across multiple datasets.
47
Yu, Chenyang, Xuehu Liu, Jiawen Zhu, Yuhao Wang, Pingping Zhang, and Huchuan Lu. "CLIMB-ReID: A Hybrid CLIP-Mamba Framework for Person Re-Identification." Proceedings of the AAAI Conference on Artificial Intelligence 39, no. 9 (2025): 9589–97. https://doi.org/10.1609/aaai.v39i9.33039.
Full textAbstract:
Person Re-IDentification (ReID) aims to identify specific persons from non-overlapping cameras. Recently, some works have suggested using large-scale pre-trained vision-language models like CLIP to boost ReID performance. Unfortunately, existing methods still struggle to address two key issues simultaneously: efficiently transferring the knowledge learned from CLIP and comprehensively extracting the context information from images or videos. To address these issues, we introduce CLIMB-ReID, a pioneering hybrid framework that synergizes the impressive power of CLIP with the remarkable computational efficiency of Mamba. Specifically, we first propose a novel Multi-Memory Collaboration (MMC) strategy to transfer CLIP's knowledge in a parameter-free and prompt-free form. Then, we design a Multi-Temporal Mamba (MTM) to capture multi-granular spatiotemporal information in videos. Finally, with Importance-aware Reorder Mamba (IRM), information from various scales is combined to produce robust sequence features. Extensive experiments show that our proposed method outperforms other state-of-the-art methods on both image and video person ReID benchmarks.
48
Wang, Xi, Xueyang Fu, Liang Li, and Zheng-Jun Zha. "DCTMamba: Advancing JPEG Image Restoration Through Long-Sequence Modeling and Adaptive Frequency Strategy." Proceedings of the AAAI Conference on Artificial Intelligence 39, no. 8 (2025): 7925–33. https://doi.org/10.1609/aaai.v39i8.32854.
Full textAbstract:
Despite the advanced long-sequence modeling of Mamba, which has expanded its applications in image restoration, there remains a lack of exploration combining its strengths with the specific characteristics of JPEG image restoration, where high-frequency components are lost after the Discrete Cosine Transform (DCT). To address this, we introduce DCTMamba, a new framework designed to apply Mamba more effectively to JPEG image restoration. Specifically, our method integrates the Discrete Cosine Transform (DCT) into the Mamba to establish the sequential scanning from lower to higher frequencies, enabling the network to initially reconstruct coarse structures and progressively refine the image with more intricate details. Furthermore, recognizing the variable frequency distributions that arise from DCT transformations across different image sizes, we have developed Scale-Adaptive Normalization to manage these variations adeptly. Comprehensive experiments confirm that DCTMamba significantly outperforms existing solutions, achieving high fidelity in both coarse structures and fine details.CTMamba significantly outperforms existing solutions, achieving high fidelity in both coarse structures and fine details.
49
Li, Zhuoyuan, Yubo Ai, Jiahao Lu, et al. "Pamba: Enhancing Global Interaction in Point Clouds via State Space Model." Proceedings of the AAAI Conference on Artificial Intelligence 39, no. 5 (2025): 5092–100. https://doi.org/10.1609/aaai.v39i5.32540.
Full textAbstract:
Transformers have demonstrated impressive results for 3D point cloud semantic segmentation. However, the quadratic complexity of transformer makes computation costs high, limiting the number of points that can be processed simultaneously and impeding the modeling of long-range dependencies between objects in a single scene. Drawing inspiration from the great potential of recent state space models (SSM) for long sequence modeling, we introduce Mamba, an SSM-based architecture, to the point cloud domain and propose Pamba, a novel architecture with strong global modeling capability under linear complexity. Specifically, to make the disorderness of point clouds fit in with the causal nature of Mamba, we propose a multi-path serialization strategy applicable to point clouds. Besides, we propose the ConvMamba block to compensate for the shortcomings of Mamba in modeling local geometries and in unidirectional modeling. Pamba obtains state-of-the-art results on several 3D point cloud segmentation tasks, including ScanNet v2, ScanNet200, S3DIS and nuScenes, while its effectiveness is validated by extensive experiments.
50
Ma, Xubo, Chuhua Huang, Xin Huang, and Wangping Wu. "Mamba-DQN: Adaptively Tunes Visual SLAM Parameters Based on Historical Observation DQN." Applied Sciences 15, no. 6 (2025): 2950. https://doi.org/10.3390/app15062950.
Full textAbstract:
The parameter configuration of traditional visual SLAM algorithms usually relies on expert experience and extensive experiments, and the parameter configuration needs to be reset as the scene changes, which is a complex and tedious process. To achieve parameter adaptation in visual SLAM, we propose the Mamba-DQN method, which transforms complex parameter adjustment tasks into policy learning assignments for the agent. In this paper, we select the key parameters of visual SLAM to construct the agent action space. The reward function is constructed based on the absolute trajectory error (ATE), and the Mamba history observer is built within the agent to learn the observation trajectory, aiming to improve the quality of the agent’s decisions. Finally, the proposed method was experimented on the EuRoc MAV and TUM-VI datasets. The experimental results show that Mamba-DQN not only enhances the positioning accuracy of visual SLAM and demonstrates good real-time performance but also avoids the tedious parameter adjustment process.