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.
MANTA: Diffusion Mamba for Efficient and Effective Stochastic Long-Term Dense Anticipation
University of Bonn(波恩大学);Birzeit University(比尔宰特大学);Toyota Motor Europe(丰田汽车欧洲公司);Lamarr Institute for Machine Learning and Artificial Intelligence(拉马尔机器学习与人工智能研究院)
AVS-Mamba: Exploring Temporal and Multi-modal Mamba for Audio-Visual Segmentation
School of Information and Communication Engineering, Dalian University of Technology(大连理工大学信息与通信工程学院);School of Innovation and Entrepreneurship, Dalian University of Technology(大连理工大学创新创业学院);School of Artificial Intelligence, Dalian University of Technology(大连理工大学人工智能学院)
Beyond Mamba: Enhancing State-space Models with Deformable Dilated Convolutions for Multi-scale Traffic Object Detection
Department of Physics, J.K. Institute of Science(J.K.科学研究所物理系);World Scientific University(世界科学出版社大学);University of Intelligent Studies(智能研究大学);School of Computer and Electronic Information, Nanjing Normal University(南京师范大学计算机与电子信息学院)
SwinMamba: A hybrid local-global mamba framework for enhancing semantic segmentation of remotely sensed images
Xi'an Jiaotong-Liverpool University(西交利物浦大学);University of Liverpool(利物浦大学);Nanyang Technological University(南洋理工大学);SJTUSME-COSMOPlat Joint Research Center for New Generation Industrial Intelligent Technology(上海交通大学机械与动力工程学院-卡奥斯新一代工业智能技术联合研究中心)
Enhancing Mamba Decoder with Bidirectional Interaction in Multi-Task Dense Prediction
National Key Laboratory of Human-Machine Hybrid Augmented Intelligence(国家人类-机器混合增强智能重点实验室);National Engineering Research Center for Visual Information and Applications(国家视觉信息与应用工程技术研究中心);Institute of Artificial Intelligence and Robotics(人工智能与机器人研究院);School of Computing and Artificial Intelligence(计算与人工智能学院);School of Electronic and Information Engineering(电子与信息工程学院)
MTMamba: Enhancing Multi-Task Dense Scene Understanding by Mamba-Based Decoders
The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州));HKUST(GZ) - SmartMore Joint Lab(香港科技大学(广州)与视博医疗联合实验室);The Hong Kong University of Science and Technology(香港科技大学);Southern University of Science and Technology(南方科技大学);SmartMore(视博医疗)
OSDMamba: Enhancing Oil Spill Detection from Remote Sensing Images Using Selective State Space Model
Department of Computer Science, University of Exeter(计算机科学系,埃克塞特大学);College of Oceanography and Space Informatics, China University of Petroleum (East China)(海洋科学与空间信息学院,中国石油大学(华东))
Enhancing Global Sensitivity and Uncertainty Quantification in Medical Image Reconstruction with Monte Carlo Arbitrary-Masked Mamba
Imperial College London(帝国理工学院);Royal Brompton Hospital(皇家布朗普顿医院);College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics(南京航空航天大学计算机科学与技术学院);School of Biomedical Engineering, Shenzhen Campus of Sun Yat-sen University(中山大学深圳校区生物医学工程学院);Human Phenome Institute, Fudan University(复旦大学人类表型组研究院);Inselspital, University of Bern(伯尔尼大学因塞尔医院);Technical University of Munich(慕尼黑工业大学)
MTMamba++: Enhancing Multi-Task Dense Scene Understanding via Mamba-Based Decoders
Artificial Intelligence Thrust, The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州)人工智能方向);Department of Computer Science and Engineering, The Hong Kong University of Science and Technology(香港科技大学计算机科学与工程系);SmartMore Corporation Limited(SmartMore有限公司)
MambaMoE: Mixture-of-Spectral-Spatial-Experts State Space Model for Hyperspectral Image Classification
School of Computer Science, Wuhan University(武汉大学计算机学院);School of Urban Design, Wuhan University(武汉大学城市设计学院);Aerospace Information Research Institute, Henan Academy of Sciences(河南科学院航天信息研究所)
U-Mamba: Enhancing Long-range Dependency for Biomedical Image Segmentation
Peter Munk Cardiac Centre, University Health Network(彼得·蒙克心脏中心,大学健康网络);University of Toronto(多伦多大学);Vector Institute for Artificial Intelligence(向量人工智能研究所)
Multi-head Spatial-Spectral Mamba for Hyperspectral Image Classification
National University of Computer and Emerging Sciences(国家计算机与新兴科学大学);Shaoxing University(绍兴大学);King Saud University(国王 Saud 大学);Innopolis University(Innopolis 大学);University of Messina(墨西拿大学)
Mamba-VA: A Mamba-based Approach for Continuous Emotion Recognition in Valence-Arousal Space
Nanjing University of Posts and Telecommunications(南京邮电大学);Nanjing University of Science and Technology(南京理工大学);ZiJin College(紫金学院);School of Computer and Artificial Intelligence(计算机与人工智能学院)
本文提出 Mamba-VA,结合 MAE、TCN 与 Mamba 建模视频情绪的局部和长程时间动态,在 ABAW VA 估计任务上优于基线。
SpineMamba: Enhancing 3D Spinal Segmentation in Clinical Imaging through Residual Visual Mamba Layers and Shape Priors
Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences(中国科学院深圳先进技术研究院);University of Chinese Academy of Sciences(中国科学院大学);Northeast Petroleum University(东北石油大学);Northeastern University(东北大学);Southern Medical University(南方医科大学)
MambaBack: Bridging Local Features and Global Contexts in Whole Slide Image Analysis
Nhu Department of Electrical Engineering and Computer Science, University of California, Irvine(加州大学尔湾分校Nhu电子工程与计算机科学系);Department of Electrical & Computer Engineering, National University of Singapore(新加坡国立大学电子与计算机工程系);PuzzleLogic Pte Ltd, Singapore(新加坡PuzzleLogic公司)
MamFusion: Multi-Mamba with Temporal Fusion for Partially Relevant Video Retrieval
Hangzhou City University(杭州城市大学);University of Wisconsin–Madison(威斯康星大学麦迪逊分校);Hangzhou Normal University(杭州师范大学);Zhejiang Provincial Engineering Research Center for Real-Time SmartTech in Urban Security Governance(浙江省实时智能安防技术工程研究中心)
DSVM-UNet : Enhancing VM-UNet with Dual Self-distillation for Medical Image Segmentation
Faculty of Military Health Service, Naval Medical University, China(海军医学院军事卫生服务学院);School of Computer Science and Technology, Shanghai University of Electric Power, China(上海电力大学计算机科学与技术学院)
MaTVLM: Hybrid Mamba-Transformer for Efficient Vision-Language Modeling
School of EIC, Huazhong University of Science & Technology(华中科技大学电子信息与通信学院);Institute of Artificial Intelligence, Huazhong University of Science & Technology(华中科技大学人工智能研究院)
InfiniMotion: Mamba Boosts Memory in Transformer for Arbitrary Long Motion Generation
Monash University(莫纳什大学);The Australian National University(澳大利亚国立大学);The University of Adelaide(阿德莱德大学);Mohamed bin Zayed University of Artificial Intelligence(穆罕默德·本·扎耶德人工智能大学);Peking University(北京大学)
Parameter Aware Mamba Model for Multi-task Dense Prediction
School of Computer Science, Dalian University of Technology(大连理工大学计算机科学学院);School of Information and Communication Engineering, Dalian University of Technology(大连理工大学信息与通信工程学院);School of Future Technology and Artificial Intelligence, Dalian University of Technology(大连理工大学未来技术与人工智能学院)
Topology-aware Mamba for Crack Segmentation in Structures
School of Computer Science and Engineering, Jiangsu University of Science and Technology(江苏科技大学计算机科学与工程学院);School of Electronic and Informatics Engineering, Jiangsu University(江苏大学电子与信息工程学院);School of Civil and Environmental Engineering, Oklahoma State University(俄克拉荷马州立大学土木与环境工程学院)
SMCD: High Realism Motion Style Transfer via Mamba-based Diffusion
Academy for Engineering and Technology, Fudan University(工程与技术学院,复旦大学);School of Computer Science and Technology, East China Normal University(计算机科学与技术学院,华东师范大学)
Fore-Mamba3D: Mamba-based Foreground-Enhanced Encoding for 3D Object Detection
School of Automation and Intelligent Sensing, Shanghai Jiao Tong University(上海交通大学自动化与智能感知学院);Institute of Image Processing and Pattern Recognition, Shanghai Jiao Tong University(上海交通大学图像处理与模式识别研究所);Institute of Medical Robotics, Shanghai Jiao Tong University(上海交通大学医学机器人研究所);School of Computer Science and Technology, Zhejiang Normal University(浙江师范大学计算机科学与技术学院);Beijing Geekplus Technology Co., Ltd(北京 Geekplus 技术有限公司)
Versatile and Efficient Medical Image Super-Resolution Via Frequency-Gated Mamba
Faculty of Engineering and Information Technology, University of Technology Sydney, Australia(工程与信息技术学院,悉尼技术大学,澳大利亚);Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, China(深圳先进技术研究所,中国科学院,中国);College of Computer Science and Technology, Qingdao University, China(计算机科学与技术学院,青岛大学,中国);Faculty of Computer Science and Control Engineering, Shenzhen University of Advanced Technology, China(计算机科学与控制工程学院,深圳先进技术大学,中国)
ZigzagPointMamba: Spatial-Semantic Mamba for Point Cloud Understanding
Key Laboratory of Signal Detection and Processing, Xinjiang University(信号检测与处理重点实验室,新疆大学);Joint International Research Laboratory of Silk Road Multilingual Cognitive Computing, Xinjiang University(丝绸之路多语种认知计算联合国际实验室,新疆大学);National Key Laboratory for Novel Software Technology, Nanjing University(新型软件技术国家重点实验室,南京大学)
M2Restore: Mixture-of-Experts-based Mamba-CNN Fusion Framework for All-in-One Image Restoration
School of Computer Science and Technology, Anhui University of Technology(安徽理工大学计算机科学与技术学院);School of Cyberspace Security, Sun Yat-sen University(中山大学网络安全学院);Tsinghua Shenzhen International Graduate School, Tsinghua University(清华大学深圳国际研究生院);School of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics(南京航空航天大学计算机科学与技术学院);College of Artificial Intelligence, Taiyuan University of Technology(太原科技大学人工智能学院)
An Empirical Study of Mamba-based Pedestrian Attribute Recognition
School of Computer Science and Technology, Anhui University(安徽大学计算机科学与技术学院);Institute of Artificial Intelligence, Hefei Comprehensive National Science Center(合肥综合性国家科学中心人工智能研究院)
Fujian Key Laboratory of Pattern Recognition(福建模式识别重点实验室);Image Understanding, Xiamen University of Technology Xiamen, China(图像理解,厦门理工大学厦门,中国);Department of Automatic Control(自动控制系);Systems Engineering, The University of Sheffield Sheffield, England(系统工程,谢菲尔德大学谢菲尔德,英格兰)
HyM-UNet: Synergizing Local Texture and Global Context via Hybrid CNN-Mamba Architecture for Medical Image Segmentation
School of Information and Communication Engineering, Beijing University of Posts and Communications (BUPT)(信息与通信工程学院,北京邮电大学);Alibaba Cloud AI Labs(阿里云人工智能实验室)
School of Advanced Technology, Xi’an Jiaotong-Liverpool University(西交利物浦大学先进技术学院);School of Electronics and Information Engineering, Beihang University(北京航空航天大学电子信息工程学院);Cambridge University(剑桥大学);Beijing Shijitan Hospital, Capital Medical University(首都医科大学附属北京世纪坛医院);University of Liverpool(利物浦大学)
A Comprehensive Survey for Hyperspectral Image Classification: The Evolution from Conventional to Transformers and Mamba Models
Department of Computer Science, National University of Computer and Emerging Sciences(计算机科学系,国立计算机与新兴科学大学);Dipartimento di Matematica e Informatica-MIFT, University of Messina(数学与信息学系-MIFT,墨西拿大学);School of Computer Science, University of Hull(计算机科学学院,赫尔大学);Institute of Software Development and Engineering, Innopolis University(软件开发与工程研究所,因诺波利斯大学);Aerospace Information Research Institute, Chinese Academy of Sciences(航空信息研究所,中国科学院);Big Geospatial Data Management, Technical University of Munich(大规模地理空间数据管理,慕尼黑技术大学);Department of Infrastructure Engineering, University of Melbourne(基础设施工程系,墨尔本大学);Intelligent Control Laboratory, PLA Rocket Force University of Engineering(智能控制实验室,中国人民解放军火箭军工程大学);Institute of Methodologies for Environmental Analysis, National Research Council(环境分析方法研究所,国家研究理事会);School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences(电子、电气与通信工程学院,中国科学院大学)