{"list":"other","total":52,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"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":"2408.03326","title":"LLaVA-OneVision: Easy Visual Task Transfer","created":"2024-08-06","cited_by_count":2719},{"id":"2304.10592","title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","created":"2023-04-20","cited_by_count":2711},{"id":"2312.14238","title":"InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks","created":"2023-12-21","cited_by_count":2565},{"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":"1610.01644","title":"Understanding intermediate layers using linear classifier probes","created":"2016-10-05","cited_by_count":1353},{"id":"2305.05665","title":"ImageBind: One Embedding Space To Bind Them All","created":"2023-05-09","cited_by_count":1175},{"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":"1801.04264","title":"Real-world Anomaly Detection in Surveillance Videos","created":"2018-01-12","cited_by_count":577},{"id":"2412.10302","title":"DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding","created":"2024-12-13","cited_by_count":572},{"id":"1712.09867","title":"Future Frame Prediction for Anomaly Detection -- A New Baseline","created":"2017-12-28","cited_by_count":391},{"id":"2502.02013","title":"Layer by Layer: Uncovering Hidden Representations in Language Models","created":"2025-02-04","cited_by_count":311},{"id":"1604.04574","title":"Learning Temporal Regularity in Video Sequences","created":"2016-04-15","cited_by_count":254},{"id":"2410.02707","title":"LLMs Know More Than They Show: On the Intrinsic Representation of LLM Hallucinations","created":"2024-10-03","cited_by_count":244},{"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":"2101.10030","title":"Weakly-supervised Video Anomaly Detection with Robust Temporal Feature Magnitude Learning","created":"2021-01-25","cited_by_count":230},{"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":"2403.02181","title":"Not All Layers of LLMs Are Necessary During Inference","created":"2024-03-04","cited_by_count":96},{"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":"2204.07974","title":"Anomaly Detection in Autonomous Driving: A Survey","created":"2022-04-17","cited_by_count":87},{"id":"2404.01014","title":"Harnessing Large Language Models for Training-free Video Anomaly Detection","created":"2024-04-01","cited_by_count":87},{"id":"2104.06689","title":"Learning Normal Dynamics in Videos with Meta Prototype Network","created":"2021-04-14","cited_by_count":71},{"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":"1908.05884","title":"GODS: Generalized One-class Discriminative Subspaces for Anomaly Detection","created":"2019-08-16","cited_by_count":64},{"id":"2402.16061","title":"How Large Language Models Encode Context Knowledge? A Layer-Wise Probing Study","created":"2024-02-25","cited_by_count":64},{"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":"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":"2401.05702","title":"Video Anomaly Detection and Explanation via Large Language Models","created":"2024-01-11","cited_by_count":47},{"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":"2406.09519","title":"Talking Heads: Understanding Inter-layer Communication in Transformer Language Models","created":"2024-06-13","cited_by_count":41},{"id":"2409.14381","title":"Investigating Layer Importance in Large Language Models","created":"2024-09-22","cited_by_count":36},{"id":"2412.09563","title":"Does Representation Matter? Exploring Intermediate Layers in Large Language Models","created":"2024-12-12","cited_by_count":34},{"id":"2305.13417","title":"VISIT: Visualizing and Interpreting the Semantic Information Flow of Transformers","created":"2023-05-22","cited_by_count":32},{"id":"2211.00882","title":"DyAnNet: A Scene Dynamicity Guided Self-Trained Video Anomaly Detection Network","created":"2022-11-02","cited_by_count":26},{"id":"2312.04333","title":"Is Bigger and Deeper Always Better? Probing LLaMA Across Scales and Layers","created":"2023-12-07","cited_by_count":20},{"id":"2307.01533","title":"Unsupervised Video Anomaly Detection with Diffusion Models Conditioned on Compact Motion Representations","created":"2023-07-04","cited_by_count":19},{"id":"1901.10364","title":"Anomaly Locality in Video Surveillance","created":"2019-01-29","cited_by_count":18},{"id":"2401.10711","title":"Weakly Supervised Gaussian Contrastive Grounding with Large Multimodal Models for Video Question Answering","created":"2024-01-19","cited_by_count":14},{"id":"2308.07050","title":"Survey on video anomaly detection in dynamic scenes with moving cameras","created":"2023-08-14","cited_by_count":10},{"id":"2501.00999","title":"Exploring Information Processing in Large Language Models: Insights from Information Bottleneck Theory","created":"2025-01-02","cited_by_count":9},{"id":"2501.02029","title":"Spot Risks Before Speaking! Unraveling Safety Attention Heads in Large Vision-Language Models","created":"2025-01-03","cited_by_count":7}],"next_cursor":null}