{"total":39,"rows":[{"id":"2407.05311","title":"MMAD: Multi-label Micro-Action Detection in Videos","created":"2024-07-07","cited_by_count":20,"area":null},{"id":"2503.15275","title":"Challenges and Trends in Egocentric Vision: A Survey","created":"2025-03-19","cited_by_count":20,"area":null},{"id":"2312.01897","title":"Adapting Short-Term Transformers for Action Detection in Untrimmed Videos","created":"2023-12-04","cited_by_count":16,"area":null},{"id":"2411.16934","title":"Online Episodic Memory Visual Query Localization with Egocentric Streaming Object Memory","created":"2024-11-25","cited_by_count":11,"area":null},{"id":"2507.09512","title":"Online Micro-gesture Recognition Using Data Augmentation and Spatial-Temporal Attention","created":"2025-07-13","cited_by_count":11,"area":null},{"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":"2504.00527","title":"SMILE: Infusing Spatial and Motion Semantics in Masked Video Learning","created":"2025-04-01","cited_by_count":9,"area":null},{"id":"2510.02262","title":"From Frames to Clips: Training-free Adaptive Key Clip Selection for Long-Form Video Understanding","created":"2025-10-02","cited_by_count":9,"area":null},{"id":"2407.17792","title":"Harnessing Temporal Causality for Advanced Temporal Action Detection","created":"2024-07-25","cited_by_count":8,"area":null},{"id":"2503.16916","title":"Temporal Action Detection Model Compression by Progressive Block Drop","created":"2025-03-21","cited_by_count":5,"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":"2401.04105","title":"Dr$^2$Net: Dynamic Reversible Dual-Residual Networks for Memory-Efficient Finetuning","created":"2024-01-08","cited_by_count":3,"area":null},{"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":"2503.06526","title":"TimeLoc: A Unified End-to-End Framework for Precise Timestamp Localization in Long Videos","created":"2025-03-09","cited_by_count":3,"area":null},{"id":"2510.13016","title":"SVAG-Bench: A Large-Scale Benchmark for Multi-Instance Spatio-temporal Video Action Grounding","created":"2025-10-14","cited_by_count":3,"area":null},{"id":"2504.14553","title":"Grounding-MD: Grounded Video-language Pre-training for Open-World Moment Detection","created":"2025-04-20","cited_by_count":2,"area":null},{"id":"2607.16284","title":"MAC 2026: Advancing Micro-Action Analysis Towards Fine-Grained Understanding","created":"2026-07-10","cited_by_count":2,"area":null},{"id":"2503.06316","title":"End-to-End Action Segmentation Transformer","created":"2025-03-08","cited_by_count":1,"area":null},{"id":"2604.20760","title":"Exploring High-Order Self-Similarity for Video Understanding","created":"2026-04-22","cited_by_count":1,"area":null},{"id":"2407.15170","title":"Semi-Supervised Pipe Video Temporal Defect Interval Localization","created":"2024-07-21","cited_by_count":0,"area":null},{"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":"2505.17555","title":"ProTAL: A Drag-and-Link Video Programming Framework for Temporal Action Localization","created":"2025-05-23","cited_by_count":0,"area":null},{"id":"2505.20739","title":"Detecting Informative Channels: ActionFormer","created":"2025-05-27","cited_by_count":0,"area":null},{"id":"2507.06411","title":"Hierarchical Multi-Stage Transformer Architecture for Context-Aware Temporal Action Localization","created":"2025-07-08","cited_by_count":0,"area":null},{"id":"2508.11955","title":"Temporal Grounding as a Learning Signal for Referring Video Object Segmentation","created":"2025-08-16","cited_by_count":0,"area":null},{"id":"2512.01128","title":"OmniFD: A Unified Model for Versatile Face Forgery Detection","created":"2025-11-30","cited_by_count":0,"area":null},{"id":"2603.12764","title":"SAVA-X: Ego-to-Exo Imitation Error Detection via Scene-Adaptive View Alignment and Bidirectional Cross View Fusion","created":"2026-03-13","cited_by_count":0,"area":null},{"id":"2603.24030","title":"Decompose and Transfer: CoT-Prompting Enhanced Alignment for Open-Vocabulary Temporal Action Detection","created":"2026-03-25","cited_by_count":0,"area":null},{"id":"2603.26780","title":"RatSeizure: A Benchmark and Saliency-Context Transformer for Rat Seizure Localization","created":"2026-03-25","cited_by_count":0,"area":null},{"id":"2604.02860","title":"A Paradigm Shift: Fully End-to-End Training for Temporal Sentence Grounding in Videos","created":"2026-04-03","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":"2604.18313","title":"Denoise and Align: Diffusion-Driven Foreground Knowledge Prompting for Open-Vocabulary Temporal Action Detection","created":"2026-04-20","cited_by_count":0,"area":null},{"id":"2605.09976","title":"OZ-TAL: Online Zero-Shot Temporal Action Localization","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2605.23355","title":"Decoupling Spatio-Temporal Adapter for Fine-Grained Badminton Action Localization","created":"2026-05-22","cited_by_count":0,"area":null},{"id":"2605.31217","title":"TALON: Token-Aligned Lightweight Adapters for 6-DoF Spacecraft Pose Estimation","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2606.12033","title":"SpikeTAD: Spiking Neural Networks for End-to-End Temporal Action Detection","created":"2026-06-10","cited_by_count":0,"area":null},{"id":"2606.14096","title":"A New Multi-Domain Benchmark for Micro-Action Recognition and Detection","created":"2026-06-12","cited_by_count":0,"area":null},{"id":"2607.04472","title":"EVAS: Efficient Multimodal Temporal Forgery Localization via Audio-Visual Synergy and Steered Boundary Calibration","created":"2026-07-05","cited_by_count":0,"area":null},{"id":"2608.22359","title":"Pre-Decoding Acoustic Triage for Budgeted Vision-Language Captioning of Untrimmed Egocentric Video","created":"2026-08-23","cited_by_count":0,"area":null}],"next_cursor":null}