{"total":36,"rows":[{"id":"2401.10166","title":"VMamba: Visual State Space Model","created":"2024-01-18","cited_by_count":969,"area":null},{"id":"2312.17235","title":"A Simple LLM Framework for Long-Range Video Question-Answering","created":"2023-12-28","cited_by_count":178,"area":null},{"id":"2403.02308","title":"Vision-RWKV: Efficient and Scalable Visual Perception with RWKV-Like Architectures","created":"2024-03-04","cited_by_count":98,"area":null},{"id":"2406.12846","title":"DrVideo: Document Retrieval Based Long Video Understanding","created":"2024-06-18","cited_by_count":65,"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":"2404.04346","title":"Koala: Key frame-conditioned long video-LLM","created":"2024-04-05","cited_by_count":57,"area":null},{"id":"2311.05908","title":"FlashFFTConv: Efficient Convolutions for Long Sequences with Tensor Cores","created":"2023-11-10","cited_by_count":33,"area":null},{"id":"2502.06020","title":"Temporal Working Memory: Query-Guided Segment Refinement for Enhanced Multimodal Understanding","created":"2025-02-09","cited_by_count":28,"area":null},{"id":"2407.21757","title":"Learning Video Context as Interleaved Multimodal Sequences","created":"2024-07-31","cited_by_count":16,"area":null},{"id":"2404.00272","title":"HSIMamba: Hyperpsectral Imaging Efficient Feature Learning with Bidirectional State Space for Classification","created":"2024-03-30","cited_by_count":14,"area":null},{"id":"2409.06299","title":"Enhancing Long Video Understanding via Hierarchical Event-Based Memory","created":"2024-09-10","cited_by_count":14,"area":null},{"id":"2406.05815","title":"What Can We Learn from State Space Models for Machine Learning on Graphs?","created":"2024-06-09","cited_by_count":13,"area":null},{"id":"2305.14952","title":"Focus Your Attention (with Adaptive IIR Filters)","created":"2023-05-24","cited_by_count":12,"area":null},{"id":"2408.17443","title":"HERMES: temporal-coHERent long-forM understanding with Episodes and Semantics","created":"2024-08-30","cited_by_count":11,"area":null},{"id":"2412.19634","title":"Deep Continuous-Time State-Space Models for Marked Event Sequences","created":"2024-12-27","cited_by_count":11,"area":null},{"id":"2405.16555","title":"Building Vision Models upon Heat Conduction","created":"2024-05-26","cited_by_count":7,"area":null},{"id":"2411.12593","title":"AdaCM$^2$: On Understanding Extremely Long-Term Video with Adaptive Cross-Modality Memory Reduction","created":"2024-11-19","cited_by_count":7,"area":null},{"id":"2412.06182","title":"Towards Long Video Understanding via Fine-detailed Video Story Generation","created":"2024-12-09","cited_by_count":6,"area":null},{"id":"2601.08602","title":"WaveFormer: Frequency-Time Decoupled Vision Modeling with Wave Equation","created":"2026-01-13","cited_by_count":5,"area":null},{"id":"2411.13683","title":"Extending Video Masked Autoencoders to 128 frames","created":"2024-11-20","cited_by_count":3,"area":null},{"id":"2412.03814","title":"Exploring Real&Synthetic Dataset and Linear Attention in Image Restoration","created":"2024-12-05","cited_by_count":3,"area":null},{"id":"2412.10002","title":"NowYouSee Me: Context-Aware Automatic Audio Description","created":"2024-12-13","cited_by_count":3,"area":null},{"id":"2508.06058","title":"Lightweight Quad Bayer HybridEVS Demosaicing via State Space Augmented Cross-Attention","created":"2025-08-08","cited_by_count":2,"area":null},{"id":"2407.01299","title":"Preserving Full Degradation Details for Blind Image Super-Resolution","created":"2024-07-01","cited_by_count":1,"area":null},{"id":"2410.09844","title":"HASN: Hybrid Attention Separable Network for Efficient Image Super-resolution","created":"2024-10-13","cited_by_count":1,"area":null},{"id":"2412.07704","title":"GEXIA: Granularity Expansion and Iterative Approximation for Scalable Multi-grained Video-language Learning","created":"2024-12-10","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":"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":"2604.10527","title":"STORM: End-to-End Referring Multi-Object Tracking in Videos","created":"2026-04-12","cited_by_count":1,"area":null},{"id":"2503.09408","title":"Diff-CL: A Novel Cross Pseudo-Supervision Method for Semi-supervised Medical Image Segmentation","created":"2025-03-12","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":"2603.01284","title":"FoSS: Modeling Long Range Dependencies and Multimodal Uncertainty in Trajectory Prediction via Fourier State Space Integration","created":"2026-03-01","cited_by_count":0,"area":null},{"id":"2604.08435","title":"HST-HGN: Heterogeneous Spatial-Temporal Hypergraph Networks with Bidirectional State Space Models for Global Fatigue Assessment","created":"2026-04-09","cited_by_count":0,"area":null},{"id":"2604.17439","title":"Attention Is not Everything: Efficient Alternatives for Vision","created":"2026-04-19","cited_by_count":0,"area":null},{"id":"2609.20181","title":"MoSSGate: Memory-Modulated State-Space Gating for Skin Lesion Segmentation","created":"2026-07-24","cited_by_count":0,"area":null}],"next_cursor":null}