{"total":135,"rows":[{"id":"2405.14174","title":"Multi-Scale VMamba: Hierarchy in Hierarchy Visual State Space Model","created":"2024-05-23","cited_by_count":62,"area":null},{"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":"2412.15691","title":"Exploiting Multimodal Spatial-temporal Patterns for Video Object Tracking","created":"2024-12-20","cited_by_count":57,"area":null},{"id":"2406.04303","title":"Vision-LSTM: xLSTM as Generic Vision Backbone","created":"2024-06-06","cited_by_count":51,"area":null},{"id":"2405.16105","title":"MambaLLIE: Implicit Retinex-Aware Low Light Enhancement with Global-then-Local State Space","created":"2024-05-25","cited_by_count":48,"area":null},{"id":"2504.05579","title":"TAPNext: Tracking Any Point (TAP) as Next Token Prediction","created":"2025-04-08","cited_by_count":37,"area":null},{"id":"2502.03738","title":"Scaling Laws in Patchification: An Image Is Worth 50,176 Tokens And More","created":"2025-02-06","cited_by_count":28,"area":null},{"id":"2503.09590","title":"BIMBA: Selective-Scan Compression for Long-Range Video Question Answering","created":"2025-03-12","cited_by_count":24,"area":null},{"id":"2407.02315","title":"VFIMamba: Video Frame Interpolation with State Space Models","created":"2024-07-02","cited_by_count":22,"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":"2404.06483","title":"RhythmMamba: Fast, Lightweight, and Accurate Remote Physiological Measurement","created":"2024-04-09","cited_by_count":20,"area":null},{"id":"2409.01071","title":"VideoLLaMB: Long Streaming Video Understanding with Recurrent Memory Bridges","created":"2024-09-02","cited_by_count":20,"area":null},{"id":"2603.08620","title":"StreamReady: Learning What to Answer and When in Long Streaming Videos","created":"2026-03-09","cited_by_count":19,"area":null},{"id":"2408.09178","title":"MambaTrack: A Simple Baseline for Multiple Object Tracking with State Space Model","created":"2024-08-17","cited_by_count":18,"area":null},{"id":"2405.07425","title":"Sakuga-42M Dataset: Scaling Up Cartoon Research","created":"2024-05-13","cited_by_count":17,"area":null},{"id":"2503.20781","title":"BASKET: A Large-Scale Video Dataset for Fine-Grained Skill Estimation","created":"2025-03-26","cited_by_count":17,"area":null},{"id":"2503.20824","title":"Exploiting Temporal State Space Sharing for Video Semantic Segmentation","created":"2025-03-26","cited_by_count":15,"area":null},{"id":"2504.13131","title":"NTIRE 2025 Challenge on Short-form UGC Video Quality Assessment and Enhancement: Methods and Results","created":"2025-04-17","cited_by_count":14,"area":null},{"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":"2410.03936","title":"Learning Truncated Causal History Model for Video Restoration","created":"2024-10-04","cited_by_count":13,"area":null},{"id":"2408.09764","title":"Event Stream based Human Action Recognition: A High-Definition Benchmark Dataset and Algorithms","created":"2024-08-19","cited_by_count":12,"area":null},{"id":"2412.13615","title":"MambaLCT: Boosting Tracking via Long-term Context State Space Model","created":"2024-12-18","cited_by_count":11,"area":null},{"id":"2404.15349","title":"A Survey on Multimodal Wearable Sensor-based Human Action Recognition","created":"2024-04-14","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":"2512.13684","title":"Recurrent Video Masked Autoencoders","created":"2025-12-15","cited_by_count":10,"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":"2509.00649","title":"MV-SSM: Multi-View State Space Modeling for 3D Human Pose Estimation","created":"2025-08-31","cited_by_count":9,"area":null},{"id":"2510.02778","title":"AdaRD-key: Adaptive Relevance-Diversity Keyframe Sampling for Long-form Video understanding","created":"2025-10-03","cited_by_count":9,"area":null},{"id":"2406.09833","title":"SHMamba: Structured Hyperbolic State Space Model for Audio-Visual Question Answering","created":"2024-06-14","cited_by_count":7,"area":null},{"id":"2410.06718","title":"MatMamba: A Matryoshka State Space Model","created":"2024-10-09","cited_by_count":7,"area":null},{"id":"2505.23617","title":"One Trajectory, One Token: Grounded Video Tokenization via Panoptic Sub-object Trajectory","created":"2025-05-29","cited_by_count":7,"area":null},{"id":"2506.06026","title":"O-MaMa: Learning Object Mask Matching between Egocentric and Exocentric Views","created":"2025-06-06","cited_by_count":7,"area":null},{"id":"2511.03325","title":"SurgViVQA: Temporally-Grounded Video Question Answering for Surgical Scene Understanding","created":"2025-11-05","cited_by_count":7,"area":null},{"id":"2408.01037","title":"MambaST: A Plug-and-Play Cross-Spectral Spatial-Temporal Fuser for Efficient Pedestrian Detection","created":"2024-08-02","cited_by_count":6,"area":null},{"id":"2409.09707","title":"Synergistic Spotting and Recognition of Micro-Expression via Temporal State Transition","created":"2024-09-15","cited_by_count":6,"area":null},{"id":"2503.14237","title":"Make Your Training Flexible: Towards Deployment-Efficient Video Models","created":"2025-03-18","cited_by_count":6,"area":null},{"id":"2504.00037","title":"ViT-Linearizer: Distilling Quadratic Knowledge into Linear-Time Vision Models","created":"2025-03-30","cited_by_count":5,"area":null},{"id":"2507.00033","title":"Moment Sampling in Video LLMs for Long-Form Video QA","created":"2025-06-18","cited_by_count":5,"area":null},{"id":"2502.16249","title":"Linear Attention for Efficient Bidirectional Sequence Modeling","created":"2025-02-22","cited_by_count":4,"area":null},{"id":"2503.06484","title":"Sign Language Translation using Frame and Event Stream: Benchmark Dataset and Algorithms","created":"2025-03-09","cited_by_count":4,"area":null},{"id":"2504.05583","title":"Gaze-Guided Learning: Avoiding Shortcut Bias in Visual Classification","created":"2025-04-08","cited_by_count":4,"area":null},{"id":"2608.30294","title":"Dynamic Hub-and-Spoke Memory for Streaming Video Understanding","created":"2026-08-31","cited_by_count":4,"area":null},{"id":"2406.04342","title":"Learning 1D Causal Visual Representation with De-focus Attention Networks","created":"2024-06-06","cited_by_count":3,"area":null},{"id":"2409.11887","title":"DocMamba: Efficient Document Pre-training with State Space Model","created":"2024-09-18","cited_by_count":3,"area":null},{"id":"2504.03501","title":"LV-MAE: Learning Long Video Representations through Masked-Embedding Autoencoders","created":"2025-04-04","cited_by_count":3,"area":null},{"id":"2507.09338","title":"Simplifying Traffic Anomaly Detection with Video Foundation Models","created":"2025-07-12","cited_by_count":3,"area":null},{"id":"2509.21265","title":"MedVSR: Medical Video Super-Resolution with Cross State-Space Propagation","created":"2025-09-25","cited_by_count":3,"area":null},{"id":"2512.16360","title":"EverybodyDance: Bipartite Graph-Based Identity Correspondence for Multi-Character Animation","created":"2025-12-18","cited_by_count":3,"area":null},{"id":"2604.14724","title":"HAMSA: Scanning-Free Vision State Space Models via SpectralPulseNet","created":"2026-04-16","cited_by_count":3,"area":null},{"id":"2408.01077","title":"PhysMamba: State Space Duality Model for Remote Physiological Measurement","created":"2024-08-02","cited_by_count":2,"area":null},{"id":"2408.10618","title":"OMEGA: Efficient Occlusion-Aware Navigation for Air-Ground Robot in Dynamic Environments via State Space Model","created":"2024-08-20","cited_by_count":2,"area":null},{"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":"2503.18637","title":"Unbiasing through Textual Descriptions: Mitigating Representation Bias in Video Benchmarks","created":"2025-03-24","cited_by_count":2,"area":null},{"id":"2504.01774","title":"Memory-efficient Low-latency Remote Photoplethysmography through Temporal-Spatial State Space Duality","created":"2025-04-02","cited_by_count":2,"area":null},{"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":"2507.10078","title":"Compression Method for Deep Diagonal State Space Model Based on $H^2$ Optimal Reduction","created":"2025-07-14","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":"2508.10522","title":"EgoMusic-driven Human Dance Motion Estimation with Skeleton Mamba","created":"2025-08-14","cited_by_count":2,"area":null},{"id":"2509.08908","title":"Diffusion-Based Action Recognition Generalizes to Untrained Domains","created":"2025-09-10","cited_by_count":2,"area":null},{"id":"2509.17901","title":"Do Modern Video-LLMs Need to Listen? A Benchmark Audit and Scalable Remedy","created":"2025-09-22","cited_by_count":2,"area":null},{"id":"2510.12160","title":"State Space Prompting via Gathering and Spreading Spatio-Temporal Information for Video Understanding","created":"2025-10-14","cited_by_count":2,"area":null},{"id":"2511.02495","title":"DetectiumFire: A Comprehensive Multi-modal Dataset Bridging Vision and Language for Fire Understanding","created":"2025-11-04","cited_by_count":2,"area":null},{"id":"2511.03725","title":"Disentangled Concepts Speak Louder Than Words: Explainable Video Action Recognition","created":"2025-11-05","cited_by_count":2,"area":null},{"id":"2605.20680","title":"DarkShake-DVS: Event-based Human Action Recognition under Low-light andShaking Camera Conditions","created":"2026-05-20","cited_by_count":2,"area":null},{"id":"2408.15679","title":"DEAR: Depth-Enhanced Action Recognition","created":"2024-08-28","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":"2412.08595","title":"Numerical Analysis of HiPPO-LegS ODE for Deep State Space Models","created":"2024-12-11","cited_by_count":1,"area":null},{"id":"2412.16602","title":"V\"Mean\"ba: Visual State Space Models only need 1 hidden dimension","created":"2024-12-21","cited_by_count":1,"area":null},{"id":"2503.11218","title":"Towards General Multimodal Visual Tracking","created":"2025-03-14","cited_by_count":1,"area":null},{"id":"2503.21782","title":"Mobile-VideoGPT: Fast and Accurate Model for Mobile Video Understanding","created":"2025-03-27","cited_by_count":1,"area":null},{"id":"2504.01257","title":"FLAMES: A Hybrid Spiking-State Space Model for Adaptive Memory Retention in Event-Based Learning","created":"2025-04-02","cited_by_count":1,"area":null},{"id":"2504.11781","title":"ACMamba: Fast Unsupervised Anomaly Detection via An Asymmetrical Consensus State Space Model","created":"2025-04-16","cited_by_count":1,"area":null},{"id":"2506.03162","title":"FuseMamba-VD: Dual Branch VideoMamba with Gated Class Token Fusion for Violence Detection","created":"2025-05-23","cited_by_count":1,"area":null},{"id":"2506.15940","title":"Polyline Path Masked Attention for Vision Transformer","created":"2025-06-19","cited_by_count":1,"area":null},{"id":"2506.19296","title":"The Effect of Depth on the Expressivity of Deep Linear State-Space Models","created":"2025-06-24","cited_by_count":1,"area":null},{"id":"2507.06603","title":"Cross-Modal Dual-Causal Learning for Long-Term Action Recognition","created":"2025-07-09","cited_by_count":1,"area":null},{"id":"2508.08082","title":"ME-TST+: Micro-expression Analysis via Temporal State Transition with ROI Relationship Awareness","created":"2025-08-11","cited_by_count":1,"area":null},{"id":"2508.18681","title":"Hierarchical Spatio-temporal Segmentation Network for Ejection Fraction Estimation in Echocardiography Videos","created":"2025-08-26","cited_by_count":1,"area":null},{"id":"2508.18834","title":"Boosting Micro-Expression Analysis via Prior-Guided Video-Level Regression","created":"2025-08-26","cited_by_count":1,"area":null},{"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":"2512.10252","title":"GDKVM: Echocardiography Video Segmentation via Spatiotemporal Key-Value Memory with Gated Delta Rule","created":"2025-12-11","cited_by_count":1,"area":null},{"id":"2601.03392","title":"Better, But Not Sufficient: Testing Video ANNs Against Macaque IT Dynamics","created":"2026-01-06","cited_by_count":1,"area":null},{"id":"2602.06017","title":"MambaVF: State Space Model for Efficient Video Fusion","created":"2026-02-05","cited_by_count":1,"area":null},{"id":"2603.11439","title":"Stay in your Lane: Role Specific Queries with Overlap Suppression Loss for Dense Video Captioning","created":"2026-03-12","cited_by_count":1,"area":null},{"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":"2605.06809","title":"LookWhen? Fast Video Recognition by Learning When, Where, and What to Compute","created":"2026-05-07","cited_by_count":1,"area":null},{"id":"2408.10488","title":"Event Stream-based Sign Language Translation: A High-Definition Benchmark Dataset and A Novel Baseline","created":"2024-08-20","cited_by_count":0,"area":null},{"id":"2408.13149","title":"Focus on Neighbors and Know the Whole: Towards Consistent Dense Multiview Text-to-Image Generator for 3D Creation","created":"2024-08-23","cited_by_count":0,"area":null},{"id":"2409.01557","title":"TASL-Net: Tri-Attention Selective Learning Network for Intelligent Diagnosis of Bimodal Ultrasound Video","created":"2024-09-03","cited_by_count":0,"area":null},{"id":"2409.07714","title":"CollaMamba: Efficient Collaborative Perception with Cross-Agent Spatial-Temporal State Space Model","created":"2024-09-12","cited_by_count":0,"area":null},{"id":"2410.03174","title":"Efficient High-Resolution Visual Representation Learning with State Space Model for Human Pose Estimation","created":"2024-10-04","cited_by_count":0,"area":null},{"id":"2411.15729","title":"OccludeNet: A Causal Journey into Mixed-View Actor-Centric Video Action Recognition under Occlusions","created":"2024-11-24","cited_by_count":0,"area":null},{"id":"2505.17807","title":"Temporal Consistency Constrained Transferable Adversarial Attacks with Background Mixup for Action Recognition","created":"2025-05-23","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":"2508.19579","title":"High-Speed FHD Full-Color Video Computer-Generated Holography","created":"2025-08-27","cited_by_count":0,"area":null},{"id":"2508.19638","title":"Beyond BEV: Optimizing Point-Level Tokens for Collaborative Perception","created":"2025-08-27","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":"2509.09151","title":"Video Understanding by Design: How Datasets Shape Video Models","created":"2025-09-11","cited_by_count":0,"area":null},{"id":"2510.24125","title":"Causal Convolutional Neural Networks as Finite Impulse Response Filters","created":"2025-10-28","cited_by_count":0,"area":null},{"id":"2511.20928","title":"Smooth regularization for efficient video recognition","created":"2025-11-25","cited_by_count":0,"area":null}],"next_cursor":"100"}