{"total":35,"rows":[{"id":"2507.00583","title":"AI-Generated Video Detection via Perceptual Straightening","created":"2025-07-01","cited_by_count":34,"area":null},{"id":"2505.18078","title":"DanceTogether! Identity-Preserving Multi-Person Interactive Video Generation","created":"2025-05-23","cited_by_count":13,"area":null},{"id":"2502.20678","title":"STPro: Spatial and Temporal Progressive Learning for Weakly Supervised Spatio-Temporal Grounding","created":"2025-02-28","cited_by_count":11,"area":null},{"id":"2501.17053","title":"Contextual Self-paced Learning for Weakly Supervised Spatio-Temporal Video Grounding","created":"2025-01-28","cited_by_count":10,"area":null},{"id":"2407.12508","title":"MERLIN: Multimodal Embedding Refinement via LLM-based Iterative Navigation for Text-Video Retrieval-Rerank Pipeline","created":"2024-07-17","cited_by_count":9,"area":null},{"id":"2505.20124","title":"TUNA: Comprehensive Fine-grained Temporal Understanding Evaluation on Dense Dynamic Videos","created":"2025-05-26","cited_by_count":9,"area":null},{"id":"2506.07603","title":"SurgBench: A Unified Large-Scale Benchmark for Surgical Video Analysis","created":"2025-06-09","cited_by_count":9,"area":null},{"id":"2505.16630","title":"SoccerChat: Integrating Multimodal Data for Enhanced Soccer Game Understanding","created":"2025-05-22","cited_by_count":8,"area":null},{"id":"2507.03578","title":"SciVid: Cross-Domain Evaluation of Video Models in Scientific Applications","created":"2025-07-04","cited_by_count":6,"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":"2508.20765","title":"Looking Beyond the Obvious: A Survey on Abstract Concept Recognition for Video Understanding","created":"2025-08-28","cited_by_count":3,"area":null},{"id":"2604.26707","title":"CurEvo: Curriculum-Guided Self-Evolution for Video Understanding","created":"2026-04-29","cited_by_count":3,"area":null},{"id":"2410.20535","title":"Asynchronous Perception Machine For Efficient Test-Time-Training","created":"2024-10-27","cited_by_count":2,"area":null},{"id":"2502.03957","title":"Improving the Perturbation-Based Explanation of Deepfake Detectors Through the Use of Adversarially-Generated Samples","created":"2025-02-06","cited_by_count":2,"area":null},{"id":"2407.13311","title":"General Vision Encoder Features as Guidance in Medical Image Registration","created":"2024-07-18","cited_by_count":1,"area":null},{"id":"2410.08299","title":"Privately Learning from Graphs with Applications in Fine-tuning Large Language Models","created":"2024-10-10","cited_by_count":1,"area":null},{"id":"2505.23952","title":"Leveraging Auxiliary Information in Text-to-Video Retrieval: A Review","created":"2025-05-29","cited_by_count":1,"area":null},{"id":"2506.20795","title":"How do Foundation Models Compare to Skeleton-Based Approaches for Gesture Recognition in Human-Robot Interaction?","created":"2025-06-25","cited_by_count":1,"area":null},{"id":"2601.05988","title":"CyberGFM: Graph Foundation Models for Lateral Movement Detection in Enterprise Networks","created":"2026-01-09","cited_by_count":1,"area":null},{"id":"2407.14069","title":"Self-Supervised Video Representation Learning in a Heuristic Decoupled Perspective","created":"2024-07-19","cited_by_count":0,"area":null},{"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":"2412.09230","title":"Foundation Models and Adaptive Feature Selection: A Synergistic Approach to Video Question Answering","created":"2024-12-12","cited_by_count":0,"area":null},{"id":"2508.03039","title":"VideoForest: Person-Anchored Hierarchical Reasoning for Cross-Video Question Answering","created":"2025-08-05","cited_by_count":0,"area":null},{"id":"2508.16527","title":"Towards Open World Detection: A Survey","created":"2025-08-22","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":"2601.04563","title":"A Vision for Multisensory Intelligence: Sensing, Science, and Synergy","created":"2026-01-08","cited_by_count":0,"area":null},{"id":"2603.12887","title":"Forecasting Epileptic Seizures from Contactless Camera via Cross-Species Transfer Learning","created":"2026-03-13","cited_by_count":0,"area":null},{"id":"2604.22476","title":"All Eyes on the Workflow: Automated and Efficient Event Discovery from Video Streams","created":"2026-04-24","cited_by_count":0,"area":null},{"id":"2604.24002","title":"IntentVLM: Open-Vocabulary Intention Recognition through Forward-Inverse Modeling with Video-Language Models","created":"2026-04-27","cited_by_count":0,"area":null},{"id":"2605.00826","title":"Understanding the Performance Plateau in Text-to-Video Retrieval: A Comprehensive Empirical and Linguistic Analysis","created":"2026-03-07","cited_by_count":0,"area":null},{"id":"2605.17095","title":"Visual Timelines of Police Encounters in Body-Worn Camera Footage: Operational Context and Activity Cataloging for Training and Analysis in OpenBWC","created":"2026-05-16","cited_by_count":0,"area":null},{"id":"2607.10299","title":"Empowering Long-form Omni-modal Understanding with Robust Audio Perception","created":"2026-07-11","cited_by_count":0,"area":null},{"id":"2607.22632","title":"VlogReward: Learning Multi-Dimensional Evaluation for Vlog Editing","created":"2026-06-19","cited_by_count":0,"area":null},{"id":"2608.30716","title":"SocialReasonBench: A Video-QA Benchmark for Social Reasoning with Counterfactual Narrative Videos","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.10355","title":"Why Is Video Still So Expensive? A Survey of Inference-Efficiency Mechanisms in Video and Audiovisual LLMs","created":"2026-09-09","cited_by_count":0,"area":null}],"next_cursor":null}