{"list":"other","total":54,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"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":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"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":"1503.03832","title":"FaceNet: A Unified Embedding for Face Recognition and Clustering","created":"2015-03-12","cited_by_count":2849},{"id":"2304.10592","title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","created":"2023-04-20","cited_by_count":2711},{"id":"1602.07332","title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","created":"2016-02-23","cited_by_count":2656},{"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":"2311.10122","title":"Video-LLaVA: Learning United Visual Representation by Alignment Before Projection","created":"2023-11-16","cited_by_count":1402},{"id":"2004.04696","title":"BLEURT: Learning Robust Metrics for Text Generation","created":"2020-04-09","cited_by_count":1203},{"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":"2304.14178","title":"mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality","created":"2023-04-27","cited_by_count":1040},{"id":"2305.06355","title":"VideoChat: Chat-Centric Video Understanding","created":"2023-05-10","cited_by_count":857},{"id":"2303.16199","title":"LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention","created":"2023-03-28","cited_by_count":781},{"id":"2404.06395","title":"MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies","created":"2024-04-09","cited_by_count":723},{"id":"1801.04264","title":"Real-world Anomaly Detection in Surveillance Videos","created":"2018-01-12","cited_by_count":577},{"id":"2305.03726","title":"Otter: A Multi-Modal Model with In-Context Instruction Tuning","created":"2023-05-05","cited_by_count":550},{"id":"1909.02622","title":"MoverScore: Text Generation Evaluating with Contextualized Embeddings and Earth Mover Distance","created":"2019-09-05","cited_by_count":418},{"id":"1712.09867","title":"Future Frame Prediction for Anomaly Detection -- A New Baseline","created":"2017-12-28","cited_by_count":391},{"id":"2305.16355","title":"PandaGPT: One Model To Instruction-Follow Them All","created":"2023-05-25","cited_by_count":334},{"id":"2003.13228","title":"Learning Memory-guided Normality for Anomaly Detection","created":"2020-03-30","cited_by_count":278},{"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":"2412.04468","title":"NVILA: Efficient Frontier Visual Language Models","created":"2024-12-05","cited_by_count":209},{"id":"2409.12961","title":"Oryx MLLM: On-Demand Spatial-Temporal Understanding at Arbitrary Resolution","created":"2024-09-19","cited_by_count":159},{"id":"2011.07491","title":"Anomaly Detection in Video via Self-Supervised and Multi-Task Learning","created":"2020-11-15","cited_by_count":148},{"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":"2302.05160","title":"Dual Memory Units with Uncertainty Regulation for Weakly Supervised Video Anomaly Detection","created":"2023-02-10","cited_by_count":90},{"id":"2404.01014","title":"Harnessing Large Language Models for Training-free Video Anomaly Detection","created":"2024-04-01","cited_by_count":87},{"id":"2412.06171","title":"Holmes-VAU: Towards Long-term Video Anomaly Understanding at Any Granularity","created":"2024-12-09","cited_by_count":70},{"id":"2303.12369","title":"Unbiased Multiple Instance Learning for Weakly Supervised Video Anomaly Detection","created":"2023-03-22","cited_by_count":64},{"id":"2305.10724","title":"Segment Any Anomaly without Training via Hybrid Prompt Regularization","created":"2023-05-18","cited_by_count":60},{"id":"1701.01546","title":"Abnormal Event Detection in Videos using Spatiotemporal Autoencoder","created":"2017-01-06","cited_by_count":57},{"id":"2407.10299","title":"Follow the Rules: Reasoning for Video Anomaly Detection with Large Language Models","created":"2024-07-14","cited_by_count":57},{"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":"2404.02072","title":"EGTR: Extracting Graph from Transformer for Scene Graph Generation","created":"2024-04-02","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":"2011.02763","title":"Robust Unsupervised Video Anomaly Detection by Multi-Path Frame Prediction","created":"2020-11-05","cited_by_count":42},{"id":"2309.13925","title":"Towards Surveillance Video-and-Language Understanding: New Dataset, Baselines, and Challenges","created":"2023-09-25","cited_by_count":42},{"id":"2303.05047","title":"Diversity-Measurable Anomaly Detection","created":"2023-03-09","cited_by_count":41},{"id":"2310.02835","title":"Delving into CLIP latent space for Video Anomaly Recognition","created":"2023-10-04","cited_by_count":27},{"id":"2409.01980","title":"Large Language Models for Anomaly and Out-of-Distribution Detection: A Survey","created":"2024-09-03","cited_by_count":27},{"id":"2311.15367","title":"BatchNorm-based Weakly Supervised Video Anomaly Detection","created":"2023-11-26","cited_by_count":22},{"id":"2403.12415","title":"VisionGPT: LLM-Assisted Real-Time Anomaly Detection for Safe Visual Navigation","created":"2024-03-19","cited_by_count":14},{"id":"2407.05910","title":"Enhancing Vision-Language Models with Scene Graphs for Traffic Accident Understanding","created":"2024-07-08","cited_by_count":10},{"id":"2503.21904","title":"AssistPDA: An Online Video Surveillance Assistant for Video Anomaly Prediction, Detection, and Analysis","created":"2025-03-27","cited_by_count":5},{"id":"2409.03236","title":"Unveiling Context-Related Anomalies: Knowledge Graph Empowered Decoupling of Scene and Action for Human-Related Video Anomaly Detection","created":"2024-09-05","cited_by_count":3}],"next_cursor":null}