{"total":108,"rows":[{"id":"2406.01188","title":"UniAnimate: Taming Unified Video Diffusion Models for Consistent Human Image Animation","created":"2024-06-03","cited_by_count":102,"area":"diffusion"},{"id":"2403.16182","title":"EgoExoLearn: A Dataset for Bridging Asynchronous Ego- and Exo-centric View of Procedural Activities in Real World","created":"2024-03-24","cited_by_count":95,"area":null},{"id":"2405.14224","title":"DiM: Diffusion Mamba for Efficient High-Resolution Image Synthesis","created":"2024-05-23","cited_by_count":72,"area":"diffusion"},{"id":"2404.09146","title":"Fusion-Mamba for Cross-modality Object Detection","created":"2024-04-14","cited_by_count":67,"area":"ssm"},{"id":"2404.09516","title":"State Space Model for New-Generation Network Alternative to Transformers: A Survey","created":"2024-04-15","cited_by_count":59,"area":null},{"id":"2405.04404","title":"Vision Mamba: A Comprehensive Survey and Taxonomy","created":"2024-05-07","cited_by_count":54,"area":"ssm"},{"id":"2407.00783","title":"Diffusion Models and Representation Learning: A Survey","created":"2024-06-30","cited_by_count":54,"area":"diffusion"},{"id":"2404.15956","title":"A Survey on Visual Mamba","created":"2024-04-24","cited_by_count":50,"area":"ssm"},{"id":"2503.04130","title":"STORM: Token-Efficient Long Video Understanding for Multimodal LLMs","created":"2025-03-06","cited_by_count":49,"area":"mllm"},{"id":"2407.09646","title":"Hamba: Single-view 3D Hand Reconstruction with Graph-guided Bi-Scanning Mamba","created":"2024-07-12","cited_by_count":45,"area":"ssm"},{"id":"2404.18861","title":"Visual Mamba: A Survey and New Outlooks","created":"2024-04-29","cited_by_count":41,"area":"ssm"},{"id":"2410.15091","title":"Spatial-Mamba: Effective Visual State Space Models via Structure-aware State Fusion","created":"2024-10-19","cited_by_count":41,"area":"ssm"},{"id":"2403.19888","title":"MambaMixer: Efficient Selective State Space Models with Dual Token and Channel Selection","created":"2024-03-29","cited_by_count":40,"area":"ssm"},{"id":"2405.15413","title":"MambaVC: Learned Visual Compression with Selective State Spaces","created":"2024-05-24","cited_by_count":28,"area":"ssm"},{"id":"2405.03025","title":"Matten: Video Generation with Mamba-Attention","created":"2024-05-05","cited_by_count":24,"area":"diffusion"},{"id":"2407.09732","title":"Speech Slytherin: Examining the Performance and Efficiency of Mamba for Speech Separation, Recognition, and Synthesis","created":"2024-07-13","cited_by_count":23,"area":"ssm"},{"id":"2502.05741","title":"Linear Attention Modeling for Learned Image Compression","created":"2025-02-09","cited_by_count":23,"area":null},{"id":"2405.15214","title":"PointRWKV: Efficient RWKV-Like Model for Hierarchical Point Cloud Learning","created":"2024-05-24","cited_by_count":21,"area":null},{"id":"2405.01726","title":"SSUMamba: Spatial-Spectral Selective State Space Model for Hyperspectral Image Denoising","created":"2024-05-02","cited_by_count":20,"area":"ssm"},{"id":"2409.01071","title":"VideoLLaMB: Long Streaming Video Understanding with Recurrent Memory Bridges","created":"2024-09-02","cited_by_count":20,"area":null},{"id":"2409.04356","title":"Serp-Mamba: Advancing High-Resolution Retinal Vessel Segmentation with Selective State-Space Model","created":"2024-09-06","cited_by_count":20,"area":"ssm"},{"id":"2503.00986","title":"Modeling Fine-Grained Hand-Object Dynamics for Egocentric Video Representation Learning","created":"2025-03-02","cited_by_count":20,"area":null},{"id":"2412.21080","title":"Vinci: A Real-time Embodied Smart Assistant based on Egocentric Vision-Language Model","created":"2024-12-30","cited_by_count":19,"area":"mllm"},{"id":"2410.03105","title":"Mamba in Vision: A Comprehensive Survey of Techniques and Applications","created":"2024-10-04","cited_by_count":18,"area":"ssm"},{"id":"2404.04933","title":"UniMD: Towards Unifying Moment Retrieval and Temporal Action Detection","created":"2024-04-07","cited_by_count":16,"area":null},{"id":"2404.11375","title":"Text-controlled Motion Mamba: Text-Instructed Temporal Grounding of Human Motion","created":"2024-04-17","cited_by_count":16,"area":"ssm"},{"id":"2501.07810","title":"AVS-Mamba: Exploring Temporal and Multi-modal Mamba for Audio-Visual Segmentation","created":"2025-01-14","cited_by_count":16,"area":"ssm"},{"id":"2407.13772","title":"GroupMamba: Efficient Group-Based Visual State Space Model","created":"2024-07-18","cited_by_count":15,"area":"ssm"},{"id":"2405.18425","title":"ViG: Linear-complexity Visual Sequence Learning with Gated Linear Attention","created":"2024-05-28","cited_by_count":13,"area":null},{"id":"2406.17815","title":"SUM: Saliency Unification through Mamba for Visual Attention Modeling","created":"2024-06-25","cited_by_count":12,"area":"ssm"},{"id":"2503.16801","title":"Auto-Regressive Diffusion for Generating 3D Human-Object Interactions","created":"2025-03-21","cited_by_count":12,"area":null},{"id":"2506.10915","title":"M4V: Multimodal Mamba for Efficient Text-to-Video Generation","created":"2025-06-12","cited_by_count":12,"area":"ssm"},{"id":"2405.14338","title":"MAMBA4D: Efficient Long-Sequence Point Cloud Video Understanding with Disentangled Spatial-Temporal State Space Models","created":"2024-05-23","cited_by_count":11,"area":"ssm"},{"id":"2404.18213","title":"S$^2$Mamba: A Spatial-spectral State Space Model for Hyperspectral Image Classification","created":"2024-04-28","cited_by_count":10,"area":"ssm"},{"id":"2502.20361","title":"OpenTAD: A Unified Framework and Comprehensive Study of Temporal Action Detection","created":"2025-02-27","cited_by_count":10,"area":null},{"id":"2508.09454","title":"Animate-X++: Universal Character Image Animation with Dynamic Backgrounds","created":"2025-08-13","cited_by_count":10,"area":null},{"id":"2406.09546","title":"QMamba: On First Exploration of Vision Mamba for Image Quality Assessment","created":"2024-06-13","cited_by_count":9,"area":"ssm"},{"id":"2501.19034","title":"XRF V2: A Dataset for Action Summarization with Wi-Fi Signals, and IMUs in Phones, Watches, Earbuds, and Glasses","created":"2025-01-31","cited_by_count":9,"area":null},{"id":"2507.02591","title":"AuroraLong: Bringing RNNs Back to Efficient Open-Ended Video Understanding","created":"2025-07-03","cited_by_count":9,"area":null},{"id":"2407.10998","title":"Discrete Diffusion Language Model for Efficient Text Summarization","created":"2024-06-25","cited_by_count":8,"area":"diffusion"},{"id":"2407.17792","title":"Harnessing Temporal Causality for Advanced Temporal Action Detection","created":"2024-07-25","cited_by_count":8,"area":null},{"id":"2501.10787","title":"LD-DETR: Loop Decoder DEtection TRansformer for Video Moment Retrieval and Highlight Detection","created":"2025-01-18","cited_by_count":8,"area":null},{"id":"2502.07161","title":"A Survey on Mamba Architecture for Vision Applications","created":"2025-02-11","cited_by_count":8,"area":"ssm"},{"id":"2506.06253","title":"Bridging Perspectives: A Survey on Cross-view Collaborative Intelligence with Egocentric-Exocentric Vision","created":"2025-06-06","cited_by_count":8,"area":null},{"id":"2507.16559","title":"Comparative validation of surgical phase recognition, instrument keypoint estimation, and instrument instance segmentation in endoscopy: Results of the PhaKIR 2024 challenge","created":"2025-07-22","cited_by_count":8,"area":null},{"id":"2605.24496","title":"EgoAction: Egocentric Action Composition with Reliability-Aware Temporal Fusion for the EPIC-KITCHENS Action Detection Challenge at CVPR 2026","created":"2026-05-23","cited_by_count":8,"area":null},{"id":"2408.10575","title":"MUSE: Mamba is Efficient Multi-scale Learner for Text-video Retrieval","created":"2024-08-20","cited_by_count":7,"area":"ssm"},{"id":"2412.12496","title":"Faster Vision Mamba is Rebuilt in Minutes via Merged Token Re-training","created":"2024-12-17","cited_by_count":5,"area":"ssm"},{"id":"2503.16916","title":"Temporal Action Detection Model Compression by Progressive Block Drop","created":"2025-03-21","cited_by_count":5,"area":null},{"id":"2506.22762","title":"VSRM: A Robust Mamba-Based Framework for Video Super-Resolution","created":"2025-06-28","cited_by_count":5,"area":"ssm"},{"id":"2501.13795","title":"Training-Free Zero-Shot Temporal Action Detection with Vision-Language Models","created":"2025-01-23","cited_by_count":4,"area":"mllm"},{"id":"2503.11392","title":"Watch and Learn: Leveraging Expert Knowledge and Language for Surgical Video Understanding","created":"2025-03-14","cited_by_count":4,"area":null},{"id":"2503.12912","title":"Pose as a Modality: A Psychology-Inspired Network for Personality Recognition with a New Multimodal Dataset","created":"2025-03-17","cited_by_count":4,"area":null},{"id":"2505.05711","title":"DiGIT: Multi-Dilated Gated Encoder and Central-Adjacent Region Integrated Decoder for Temporal Action Detection Transformer","created":"2025-05-09","cited_by_count":4,"area":null},{"id":"2506.23283","title":"MoMa: Modulating Mamba for Adapting Image Foundation Models to Video Recognition","created":"2025-06-29","cited_by_count":4,"area":"ssm"},{"id":"2511.17929","title":"MambaTAD: When State-Space Models Meet Long-Range Temporal Action Detection","created":"2025-11-22","cited_by_count":4,"area":"ssm"},{"id":"2407.13078","title":"Enhancing Temporal Action Localization: Advanced S6 Modeling with Recurrent Mechanism","created":"2024-07-18","cited_by_count":3,"area":null},{"id":"2408.10679","title":"Alignment-free Raw Video Demoireing","created":"2024-08-20","cited_by_count":3,"area":"ssm"},{"id":"2412.09202","title":"Temporal Action Localization with Cross Layer Task Decoupling and Refinement","created":"2024-12-12","cited_by_count":3,"area":null},{"id":"2602.17869","title":"Learning Compact Video Representations for Efficient Long-form Video Understanding in Large Multimodal Models","created":"2026-02-19","cited_by_count":3,"area":"mllm"},{"id":"2603.00439","title":"Mamba-CAD: State Space Model For 3D Computer-Aided Design Generative Modeling","created":"2026-02-28","cited_by_count":3,"area":"ssm"},{"id":"2406.08486","title":"On Evaluating Adversarial Robustness of Volumetric Medical Segmentation Models","created":"2024-06-12","cited_by_count":2,"area":"ssm"},{"id":"2501.06138","title":"MS-Temba: Multi-Scale Temporal Mamba for Understanding Long Untrimmed Videos","created":"2025-01-10","cited_by_count":2,"area":"ssm"},{"id":"2503.11224","title":"Technologies on Effectiveness and Efficiency: A Survey of State Spaces Models","created":"2025-03-14","cited_by_count":2,"area":null},{"id":"2504.16003","title":"MVQA: Mamba with Unified Sampling for Efficient Video Quality Assessment","created":"2025-04-22","cited_by_count":2,"area":"ssm"},{"id":"2505.22535","title":"RiverMamba: A State Space Model for Global River Discharge and Flood Forecasting","created":"2025-05-28","cited_by_count":2,"area":null},{"id":"2507.23595","title":"MamV2XCalib: V2X-based Target-less Infrastructure Camera Calibration with State Space Model","created":"2025-07-31","cited_by_count":2,"area":null},{"id":"2405.20917","title":"Learning to Estimate System Specifications in Linear Temporal Logic using Transformers and Mamba","created":"2024-05-31","cited_by_count":1,"area":"ssm"},{"id":"2406.16722","title":"Venturing into Uncharted Waters: The Navigation Compass from Transformer to Mamba","created":"2024-06-24","cited_by_count":1,"area":"ssm"},{"id":"2408.11318","title":"TWLV-I: Analysis and Insights from Holistic Evaluation on Video Foundation Models","created":"2024-08-21","cited_by_count":1,"area":null},{"id":"2410.24075","title":"Identifying Spatio-Temporal Drivers of Extreme Events","created":"2024-10-31","cited_by_count":1,"area":null},{"id":"2411.19544","title":"SkelMamba: A State Space Model for Efficient Skeleton Action Recognition of Neurological Disorders","created":"2024-11-29","cited_by_count":1,"area":null},{"id":"2507.16342","title":"Mamba-OTR: a Mamba-based Solution for Online Take and Release Detection from Untrimmed Egocentric Video","created":"2025-07-22","cited_by_count":1,"area":"ssm"},{"id":"2509.11394","title":"MixANT: Observation-dependent Memory Propagation for Stochastic Dense Action Anticipation","created":"2025-09-14","cited_by_count":1,"area":null},{"id":"2509.24318","title":"Similarity-Aware Selective State-Space Modeling for Semantic Correspondence","created":"2025-09-29","cited_by_count":1,"area":"ssm"},{"id":"2510.10478","title":"MSF-Mamba: Motion-aware State Fusion Mamba for Efficient Micro-Gesture Recognition","created":"2025-10-12","cited_by_count":1,"area":"ssm"},{"id":"2602.06017","title":"MambaVF: State Space Model for Efficient Video Fusion","created":"2026-02-05","cited_by_count":1,"area":null},{"id":"2603.24295","title":"RS-SSM: Refining Forgotten Specifics in State Space Model for Video Semantic Segmentation","created":"2026-03-25","cited_by_count":1,"area":"ssm"},{"id":"2604.18274","title":"LiquidTAD: Efficient Temporal Action Detection via Parallel Liquid-Inspired Temporal Relaxation","created":"2026-04-20","cited_by_count":1,"area":null},{"id":"2408.05606","title":"Exploring Applications of State Space Models and Advanced Training Techniques in Sequential Recommendations: A Comparative Study on Efficiency and Performance","created":"2024-08-10","cited_by_count":0,"area":null},{"id":"2408.17081","title":"Stochastic Layer-Wise Shuffle for Improving Vision Mamba Training","created":"2024-08-30","cited_by_count":0,"area":"ssm"},{"id":"2409.11867","title":"StableMamba: Distillation-free Scaling of Large SSMs for Images and Videos","created":"2024-09-18","cited_by_count":0,"area":"ssm"},{"id":"2410.14993","title":"Making Every Frame Matter: Continuous Activity Recognition in Streaming Video via Adaptive Video Context Modeling","created":"2024-10-19","cited_by_count":0,"area":null},{"id":"2411.00233","title":"SambaMixer: State of Health Prediction of Li-ion Batteries using Mamba State Space Models","created":"2024-10-31","cited_by_count":0,"area":"ssm"},{"id":"2504.00647","title":"FDDet: Frequency-Decoupling for Boundary Refinement in Temporal Action Detection","created":"2025-04-01","cited_by_count":0,"area":null},{"id":"2506.10242","title":"DySS: Dynamic Queries and State-Space Learning for Efficient 3D Object Detection from Multi-Camera Videos","created":"2025-06-11","cited_by_count":0,"area":null},{"id":"2507.13326","title":"A Real-Time System for Egocentric Hand-Object Interaction Detection in Industrial Domains","created":"2025-07-17","cited_by_count":0,"area":null},{"id":"2508.11313","title":"Denoise-then-Retrieve: Text-Conditioned Video Denoising for Video Moment Retrieval","created":"2025-08-15","cited_by_count":0,"area":null},{"id":"2509.03426","title":"Time-Scaling State-Space Models for Dense Video Captioning","created":"2025-09-03","cited_by_count":0,"area":null},{"id":"2509.04824","title":"Exploring Non-Local Spatial-Angular Correlations with a Hybrid Mamba-Transformer Framework for Light Field Super-Resolution","created":"2025-09-05","cited_by_count":0,"area":"ssm"},{"id":"2510.00862","title":"Gather-Scatter Mamba: Accelerating Propagation with Efficient State Space Model","created":"2025-10-01","cited_by_count":0,"area":"ssm"},{"id":"2511.14503","title":"Parameter Aware Mamba Model for Multi-task Dense Prediction","created":"2025-11-18","cited_by_count":0,"area":"ssm"},{"id":"2512.07756","title":"UltrasODM: A Dual Stream Optical Flow Mamba Network for 3D Freehand Ultrasound Reconstruction","created":"2025-12-08","cited_by_count":0,"area":"ssm"},{"id":"2512.15038","title":"LADY: Linear Attention for Autonomous Driving Efficiency without Transformers","created":"2025-12-17","cited_by_count":0,"area":"driving"},{"id":"2603.04882","title":"DeformTrace: A Deformable State Space Model with Relay Tokens for Temporal Forgery Localization","created":"2026-03-05","cited_by_count":0,"area":null},{"id":"2604.09164","title":"Efficient Spatial-Temporal Focal Adapter with SSM for Temporal Action Detection","created":"2026-04-10","cited_by_count":0,"area":null},{"id":"2604.26461","title":"$\\text{PKS}^4$:Parallel Kinematic Selective State Space Scanners for Efficient Video Understanding","created":"2026-04-29","cited_by_count":0,"area":"ssm"},{"id":"2604.27591","title":"ClipTBP: Clip-Pair based Temporal Boundary Prediction with Boundary-Aware Learning for Moment Retrieval","created":"2026-04-30","cited_by_count":0,"area":null},{"id":"2605.22695","title":"Improving Viewpoint-Invariance and Temporal Consistency for Action Detection","created":"2026-05-21","cited_by_count":0,"area":null},{"id":"2605.24302","title":"Cross-Modal Action Recognition in Egocentric Video Using Mamba: Integrating RGB and Hand Skeleton Streams via CLS Token Fusion Strategies","created":"2026-05-23","cited_by_count":0,"area":"ssm"}],"next_cursor":"100"}