{"list":"other","total":51,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"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":"1411.5726","title":"CIDEr: Consensus-based Image Description Evaluation","created":"2014-11-20","cited_by_count":2046},{"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":"2405.21075","title":"Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis","created":"2024-05-31","cited_by_count":1413},{"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":"2404.16821","title":"How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites","created":"2024-04-25","cited_by_count":1050},{"id":"2305.06355","title":"VideoChat: Chat-Centric Video Understanding","created":"2023-05-10","cited_by_count":857},{"id":"2406.07476","title":"VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs","created":"2024-06-11","cited_by_count":771},{"id":"2410.02713","title":"LLaVA-Video: Video Instruction Tuning With Synthetic Data","created":"2024-10-03","cited_by_count":583},{"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":"2004.06704","title":"FineGym: A Hierarchical Video Dataset for Fine-grained Action Understanding","created":"2020-04-14","cited_by_count":234},{"id":"2101.10030","title":"Weakly-supervised Video Anomaly Detection with Robust Temporal Feature Magnitude Learning","created":"2021-01-25","cited_by_count":230},{"id":"2406.14515","title":"MMBench-Video: A Long-Form Multi-Shot Benchmark for Holistic Video Understanding","created":"2024-06-20","cited_by_count":182},{"id":"1903.07256","title":"Graph Convolutional Label Noise Cleaner: Train a Plug-and-play Action Classifier for Anomaly Detection","created":"2019-03-18","cited_by_count":171},{"id":"2104.01633","title":"MIST: Multiple Instance Self-Training Framework for Video Anomaly Detection","created":"2021-04-04","cited_by_count":138},{"id":"2108.06852","title":"A Hybrid Video Anomaly Detection Framework via Memory-Augmented Flow Reconstruction and Flow-Guided Frame Prediction","created":"2021-08-16","cited_by_count":129},{"id":"2203.03962","title":"Generative Cooperative Learning for Unsupervised Video Anomaly Detection","created":"2022-03-08","cited_by_count":102},{"id":"2302.05160","title":"Dual Memory Units with Uncertainty Regulation for Weakly Supervised Video Anomaly Detection","created":"2023-02-10","cited_by_count":90},{"id":"2211.15098","title":"MGFN: Magnitude-Contrastive Glance-and-Focus Network for Weakly-Supervised Video Anomaly Detection","created":"2022-11-28","cited_by_count":89},{"id":"2402.13250","title":"Video ReCap: Recursive Captioning of Hour-Long Videos","created":"2024-02-20","cited_by_count":89},{"id":"2404.01014","title":"Harnessing Large Language Models for Training-free Video Anomaly Detection","created":"2024-04-01","cited_by_count":87},{"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":"2301.02311","title":"HierVL: Learning Hierarchical Video-Language Embeddings","created":"2023-01-05","cited_by_count":66},{"id":"1908.05884","title":"GODS: Generalized One-class Discriminative Subspaces for Anomaly Detection","created":"2019-08-16","cited_by_count":64},{"id":"2303.12369","title":"Unbiased Multiple Instance Learning for Weakly Supervised Video Anomaly Detection","created":"2023-03-22","cited_by_count":64},{"id":"2105.11107","title":"FineAction: A Fine-Grained Video Dataset for Temporal Action Localization","created":"2021-05-24","cited_by_count":61},{"id":"2311.07042","title":"Open-Vocabulary Video Anomaly Detection","created":"2023-11-13","cited_by_count":57},{"id":"2304.05112","title":"Video Event Restoration Based on Keyframes for Video Anomaly Detection","created":"2023-04-11","cited_by_count":54},{"id":"2404.08531","title":"Text Prompt with Normality Guidance for Weakly Supervised Video Anomaly Detection","created":"2024-04-12","cited_by_count":49},{"id":"2405.16886","title":"Hawk: Learning to Understand Open-World Video Anomalies","created":"2024-05-27","cited_by_count":49},{"id":"2401.05702","title":"Video Anomaly Detection and Explanation via Large Language Models","created":"2024-01-11","cited_by_count":47},{"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":"2306.14451","title":"Learning Prompt-Enhanced Context Features for Weakly-Supervised Video Anomaly Detection","created":"2023-06-26","cited_by_count":43},{"id":"2309.13925","title":"Towards Surveillance Video-and-Language Understanding: New Dataset, Baselines, and Challenges","created":"2023-09-25","cited_by_count":42},{"id":"2103.01302","title":"Coarse-Fine Networks for Temporal Activity Detection in Videos","created":"2021-03-01","cited_by_count":28},{"id":"2211.00882","title":"DyAnNet: A Scene Dynamicity Guided Self-Trained Video Anomaly Detection Network","created":"2022-11-02","cited_by_count":26},{"id":"2304.05841","title":"Exploring Diffusion Models for Unsupervised Video Anomaly Detection","created":"2023-04-12","cited_by_count":23},{"id":"1901.10364","title":"Anomaly Locality in Video Surveillance","created":"2019-01-29","cited_by_count":18},{"id":"2308.12608","title":"HR-Pro: Point-supervised Temporal Action Localization via Hierarchical Reliability Propagation","created":"2023-08-24","cited_by_count":16},{"id":"2204.03017","title":"Learning from Untrimmed Videos: Self-Supervised Video Representation Learning with Hierarchical Consistency","created":"2022-04-06","cited_by_count":15},{"id":"2207.00887","title":"Towards Robust Video Object Segmentation with Adaptive Object Calibration","created":"2022-07-02","cited_by_count":11},{"id":"2403.06154","title":"GlanceVAD: Exploring Glance Supervision for Label-efficient Video Anomaly Detection","created":"2024-03-10","cited_by_count":7}],"next_cursor":null}