{"total":32,"rows":[{"id":"2405.16886","title":"Hawk: Learning to Understand Open-World Video Anomalies","created":"2024-05-27","cited_by_count":49,"area":null},{"id":"2409.05383","title":"Deep Learning for Video Anomaly Detection: A Review","created":"2024-09-09","cited_by_count":27,"area":null},{"id":"2507.09313","title":"ProactiveVideoQA: A Comprehensive Benchmark Evaluating Proactive Interactions in Video Large Language Models","created":"2025-07-12","cited_by_count":27,"area":null},{"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":"2505.12589","title":"SurveillanceVQA-589K: A Benchmark for Comprehensive Surveillance Video-Language Understanding with Large Models","created":"2025-05-19","cited_by_count":18,"area":null},{"id":"2411.17776","title":"Beyond Walking: A Large-Scale Image-Text Benchmark for Text-based Person Anomaly Search","created":"2024-11-26","cited_by_count":11,"area":null},{"id":"2412.14056","title":"A Review of Multimodal Explainable Artificial Intelligence: Past, Present and Future","created":"2024-12-18","cited_by_count":9,"area":null},{"id":"2507.17394","title":"HiProbe-VAD: Video Anomaly Detection via Hidden States Probing in Tuning-Free Multimodal LLMs","created":"2025-07-23","cited_by_count":9,"area":null},{"id":"2503.13160","title":"Language-guided Open-world Video Anomaly Detection under Weak Supervision","created":"2025-03-17","cited_by_count":8,"area":null},{"id":"2602.19248","title":"No Need For Real Anomaly: MLLM Empowered Zero-Shot Video Anomaly Detection","created":"2026-02-22","cited_by_count":8,"area":null},{"id":"2512.05060","title":"4DLangVGGT: 4D Language-Visual Geometry Grounded Transformer","created":"2025-12-04","cited_by_count":5,"area":null},{"id":"2507.21649","title":"The Evolution of Video Anomaly Detection: A Unified Framework from DNN to MLLM","created":"2025-07-29","cited_by_count":4,"area":null},{"id":"2511.07299","title":"VADER: Towards Causal Video Anomaly Understanding with Relation-Aware Large Language Models","created":"2025-11-10","cited_by_count":4,"area":null},{"id":"2512.17601","title":"HeadHunt-VAD: Hunting Robust Anomaly-Sensitive Heads in MLLM for Tuning-Free Video Anomaly Detection","created":"2025-12-19","cited_by_count":4,"area":null},{"id":"2604.23282","title":"Bridging the Pose-Semantic Gap: A Cascade Framework for Text-Based Person Anomaly Search","created":"2026-04-25","cited_by_count":4,"area":null},{"id":"2310.02894","title":"Human-centric Behavior Description in Videos: New Benchmark and Model","created":"2023-10-04","cited_by_count":3,"area":null},{"id":"2505.19022","title":"Rethinking Metrics and Benchmarks of Video Anomaly Detection","created":"2025-05-25","cited_by_count":3,"area":null},{"id":"2601.17258","title":"FineVAU: A Novel Human-Aligned Benchmark for Fine-Grained Video Anomaly Understanding","created":"2026-01-24","cited_by_count":3,"area":null},{"id":"2403.01169","title":"Learn Suspected Anomalies from Event Prompts for Video Anomaly Detection","created":"2024-03-02","cited_by_count":2,"area":null},{"id":"2407.20642","title":"Effectively Leveraging CLIP for Generating Situational Summaries of Images and Videos","created":"2024-07-30","cited_by_count":2,"area":null},{"id":"2506.01466","title":"Towards Scalable Video Anomaly Retrieval: A Synthetic Video-Text Benchmark","created":"2025-06-02","cited_by_count":2,"area":null},{"id":"2509.11605","title":"DUAL-VAD: Dual Benchmarks and Anomaly-Focused Sampling for Video Anomaly Detection","created":"2025-09-15","cited_by_count":2,"area":null},{"id":"2511.00524","title":"Text-guided Fine-Grained Video Anomaly Understanding","created":"2025-11-01","cited_by_count":2,"area":null},{"id":"2512.20070","title":"Progressive Learned Image Compression for Machine Perception","created":"2025-12-23","cited_by_count":1,"area":null},{"id":"2602.10549","title":"Enhancing Weakly Supervised Multimodal Video Anomaly Detection through Text Guidance","created":"2026-02-11","cited_by_count":1,"area":null},{"id":"2603.22872","title":"ForeSea: AI Forensic Search with Multi-modal Queries for Video Surveillance","created":"2026-03-24","cited_by_count":1,"area":null},{"id":"2604.07772","title":"ESOM: Efficiently Understanding Streaming Video Anomalies with Open-world Dynamic Definitions","created":"2026-04-09","cited_by_count":1,"area":null},{"id":"2608.05699","title":"TAU-Bench: From Anomaly Instance Tracking to Fine-Grained Video Anomaly Understanding","created":"2026-08-06","cited_by_count":1,"area":null},{"id":"2503.14228","title":"Panoramic Distortion-Aware Tokenization for Person Detection and Localization in Overhead Fisheye Images","created":"2025-03-18","cited_by_count":0,"area":null},{"id":"2508.07330","title":"Planner-Refiner: Dynamic Space-Time Refinement for Vision-Language Alignment in Videos","created":"2025-08-10","cited_by_count":0,"area":null},{"id":"2605.25806","title":"An Analysis Focused on Womens Safety: Can VAD Models Be Enhanced by a Multi-modal Dataset?","created":"2026-05-25","cited_by_count":0,"area":null},{"id":"2609.06978","title":"AnomalyCraft-700K: Component-Level Controllable and Verifiable Synthetic Anomalies for Fine-Grained Video Anomaly Understanding","created":"2026-09-07","cited_by_count":0,"area":null}],"next_cursor":null}