{"list":"other","total":54,"rows":[{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"id":"2409.12191","title":"Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution","created":"2024-09-18","cited_by_count":4234},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"2303.15343","title":"Sigmoid Loss for Language Image Pre-Training","created":"2023-03-27","cited_by_count":3109},{"id":"1411.5726","title":"CIDEr: Consensus-based Image Description Evaluation","created":"2014-11-20","cited_by_count":2046},{"id":"2412.05271","title":"Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling","created":"2024-12-06","cited_by_count":1599},{"id":"2306.02858","title":"Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding","created":"2023-06-05","cited_by_count":1471},{"id":"2311.10122","title":"Video-LLaVA: Learning United Visual Representation by Alignment Before Projection","created":"2023-11-16","cited_by_count":1402},{"id":"2306.05424","title":"Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models","created":"2023-06-08","cited_by_count":1062},{"id":"2407.07726","title":"PaliGemma: A versatile 3B VLM for transfer","created":"2024-07-10","cited_by_count":696},{"id":"1801.04264","title":"Real-world Anomaly Detection in Surveillance Videos","created":"2018-01-12","cited_by_count":577},{"id":"1904.02639","title":"Memorizing Normality to Detect Anomaly: Memory-augmented Deep Autoencoder for Unsupervised Anomaly Detection","created":"2019-04-04","cited_by_count":564},{"id":"1712.09867","title":"Future Frame Prediction for Anomaly Detection -- A New Baseline","created":"2017-12-28","cited_by_count":391},{"id":"1604.04574","title":"Learning Temporal Regularity in Video Sequences","created":"2016-04-15","cited_by_count":254},{"id":"2007.04687","title":"Not only Look, but also Listen: Learning Multimodal Violence Detection under Weak Supervision","created":"2020-07-09","cited_by_count":238},{"id":"2406.11816","title":"VideoLLM-online: Online Video Large Language Model for Streaming Video","created":"2024-06-17","cited_by_count":225},{"id":"2412.04468","title":"NVILA: Efficient Frontier Visual Language Models","created":"2024-12-05","cited_by_count":209},{"id":"2406.08085","title":"Flash-VStream: Memory-Based Real-Time Understanding for Long Video Streams","created":"2024-06-12","cited_by_count":169},{"id":"2405.16009","title":"Streaming Long Video Understanding with Large Language Models","created":"2024-05-25","cited_by_count":167},{"id":"2501.03218","title":"Dispider: Enabling Video LLMs with Active Real-Time Interaction via Disentangled Perception, Decision, and Reaction","created":"2025-01-06","cited_by_count":127},{"id":"2308.11681","title":"VadCLIP: Adapting Vision-Language Models for Weakly Supervised Video Anomaly Detection","created":"2023-08-22","cited_by_count":123},{"id":"2403.18406","title":"An Image Grid Can Be Worth a Video: Zero-shot Video Question Answering Using a VLM","created":"2024-03-27","cited_by_count":97},{"id":"2510.09608","title":"StreamingVLM: Real-Time Understanding for Infinite Video Streams","created":"2025-10-10","cited_by_count":95},{"id":"2404.01014","title":"Harnessing Large Language Models for Training-free Video Anomaly Detection","created":"2024-04-01","cited_by_count":87},{"id":"2509.24871","title":"StreamForest: Efficient Online Video Understanding with Persistent Event Memory","created":"2025-09-29","cited_by_count":78},{"id":"2501.13468","title":"Streaming Video Understanding and Multi-round Interaction with Memory-enhanced Knowledge","created":"2025-01-23","cited_by_count":73},{"id":"2412.06171","title":"Holmes-VAU: Towards Long-term Video Anomaly Understanding at Any Granularity","created":"2024-12-09","cited_by_count":70},{"id":"2212.05136","title":"CLIP-TSA: CLIP-Assisted Temporal Self-Attention for Weakly-Supervised Video Anomaly Detection","created":"2022-12-09","cited_by_count":67},{"id":"2406.12235","title":"Holmes-VAD: Towards Unbiased and Explainable Video Anomaly Detection via Multi-modal LLM","created":"2024-06-18","cited_by_count":64},{"id":"2506.15745","title":"InfiniPot-V: Memory-Constrained KV Cache Compression for Streaming Video Understanding","created":"2025-06-18","cited_by_count":58},{"id":"2508.15717","title":"StreamMem: Query-Agnostic KV Cache Memory for Streaming Video Understanding","created":"2025-08-21","cited_by_count":58},{"id":"2503.06220","title":"StreamMind: Unlocking Full Frame Rate Streaming Video Dialogue through Event-Gated Cognition","created":"2025-03-08","cited_by_count":46},{"id":"2405.00181","title":"Uncovering What, Why and How: A Comprehensive Benchmark for Causation Understanding of Video Anomaly","created":"2024-04-30","cited_by_count":45},{"id":"2305.13611","title":"A New Comprehensive Benchmark for Semi-supervised Video Anomaly Detection and Anticipation","created":"2023-05-23","cited_by_count":42},{"id":"2504.13092","title":"EventVAD: Training-Free Event-Aware Video Anomaly Detection","created":"2025-04-17","cited_by_count":36},{"id":"2412.01095","title":"VERA: Explainable Video Anomaly Detection via Verbalized Learning of Vision-Language Models","created":"2024-12-02","cited_by_count":24},{"id":"2505.19877","title":"Vad-R1: Towards Video Anomaly Reasoning via Perception-to-Cognition Chain-of-Thought","created":"2025-05-26","cited_by_count":24},{"id":"2505.23504","title":"VAU-R1: Advancing Video Anomaly Understanding via Reinforcement Fine-Tuning","created":"2025-05-29","cited_by_count":24},{"id":"2504.13915","title":"Memory-efficient Streaming VideoLLMs for Real-time Procedural Video Understanding","created":"2025-04-10","cited_by_count":19},{"id":"2509.26386","title":"PANDA: Towards Generalist Video Anomaly Detection via Agentic AI Engineer","created":"2025-09-30","cited_by_count":19},{"id":"2503.04504","title":"AnyAnomaly: Zero-Shot Customizable Video Anomaly Detection with LVLM","created":"2025-03-06","cited_by_count":15},{"id":"2505.15205","title":"Flashback: Memory-Driven Zero-shot, Real-time Video Anomaly Detection","created":"2025-05-21","cited_by_count":12},{"id":"2511.00962","title":"A Unified Reasoning Framework for Holistic Zero-Shot Video Anomaly Analysis","created":"2025-11-02","cited_by_count":12},{"id":"2404.07887","title":"Context-aware Video Anomaly Detection in Long-Term Datasets","created":"2024-04-11","cited_by_count":11},{"id":"2510.21449","title":"MoniTor: Exploiting Large Language Models with Instruction for Online Video Anomaly Detection","created":"2025-10-24","cited_by_count":11},{"id":"2504.20041","title":"Learning Streaming Video Representation via Multitask Training","created":"2025-04-28","cited_by_count":10},{"id":"2503.13160","title":"Language-guided Open-world Video Anomaly Detection under Weak Supervision","created":"2025-03-17","cited_by_count":8},{"id":"2506.05175","title":"Track Any Anomalous Object: A Granular Video Anomaly Detection Pipeline","created":"2025-06-05","cited_by_count":8},{"id":"2508.06350","title":"Aligning Effective Tokens with Video Anomaly in Large Language Models","created":"2025-08-08","cited_by_count":8},{"id":"2509.12145","title":"Open-ended Hierarchical Streaming Video Understanding with Vision Language Models","created":"2025-09-15","cited_by_count":6},{"id":"2509.23724","title":"Video Panels for Long Video Understanding","created":"2025-09-28","cited_by_count":6},{"id":"2511.07299","title":"VADER: Towards Causal Video Anomaly Understanding with Relation-Aware Large Language Models","created":"2025-11-10","cited_by_count":4},{"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}],"next_cursor":null}