{"total":19,"rows":[{"id":"2505.23504","title":"VAU-R1: Advancing Video Anomaly Understanding via Reinforcement Fine-Tuning","created":"2025-05-29","cited_by_count":24,"area":null},{"id":"2412.13845","title":"Do Language Models Understand Time?","created":"2024-12-18","cited_by_count":14,"area":null},{"id":"2511.00962","title":"A Unified Reasoning Framework for Holistic Zero-Shot Video Anomaly Analysis","created":"2025-11-02","cited_by_count":12,"area":null},{"id":"2504.04495","title":"AVadCLIP: Audio-Visual Collaboration for Robust Video Anomaly Detection","created":"2025-04-06","cited_by_count":7,"area":null},{"id":"2506.20342","title":"Feature Hallucination for Self-supervised Action Recognition","created":"2025-06-25","cited_by_count":3,"area":null},{"id":"2511.12321","title":"Learning Time in Static Classifiers","created":"2025-11-15","cited_by_count":2,"area":null},{"id":"2501.02593","title":"Evolving Skeletons: Motion Dynamics in Action Recognition","created":"2025-01-05","cited_by_count":1,"area":null},{"id":"2502.16233","title":"Graph Self-Supervised Learning with Learnable Structural and Positional Encodings","created":"2025-02-22","cited_by_count":1,"area":null},{"id":"2505.02393","title":"Uncertainty-Weighted Fusion of Image and Synthetic Event for Video Anomaly Detection","created":"2025-05-05","cited_by_count":1,"area":null},{"id":"2603.22757","title":"Multimodal Industrial Anomaly Detection via Geometric Prior","created":"2026-03-24","cited_by_count":1,"area":null},{"id":"2609.17211","title":"Probe-VAD: Ordinal Likelihood Probing for Training-Free Video Anomaly Detection","created":"2026-09-15","cited_by_count":1,"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":"2602.21944","title":"Learning to Fuse and Reconstruct Multi-View Graphs for Diabetic Retinopathy Grading","created":"2026-02-25","cited_by_count":0,"area":null},{"id":"2603.19546","title":"Subspace Kernel Learning on Tensor Sequences","created":"2026-03-20","cited_by_count":0,"area":null},{"id":"2605.08651","title":"Privacy-Aware Video Anomaly Detection through Orthogonal Subspace Projection","created":"2026-05-09","cited_by_count":0,"area":null},{"id":"2605.25119","title":"Trust-Aware Joint Feature-Prediction Discrepancy for Robust Domain Adaptation","created":"2026-05-24","cited_by_count":0,"area":null},{"id":"2605.25488","title":"Test-Time Self-Adaptive Conditioning for Stable Audio-Driven Talking-Head Generation","created":"2026-05-25","cited_by_count":0,"area":null},{"id":"2609.40014","title":"Can We Anticipate Violence? Multimodal Learning from Pre-Incident Behavioral Cues","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.16324","title":"Anomaly-Guided Observation and Two-Level Semantic Feedback for Training-Free Video Anomaly Analysis","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}