{"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":"1612.00837","title":"Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering","created":"2016-12-02","cited_by_count":2516},{"id":"1505.00468","title":"VQA: Visual Question Answering","created":"2015-05-03","cited_by_count":2506},{"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":"1612.06890","title":"CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning","created":"2016-12-20","cited_by_count":1457},{"id":"2311.10122","title":"Video-LLaVA: Learning United Visual Representation by Alignment Before Projection","created":"2023-11-16","cited_by_count":1402},{"id":"2305.05665","title":"ImageBind: One Embedding Space To Bind Them All","created":"2023-05-09","cited_by_count":1175},{"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":"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":"2207.14315","title":"SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentation","created":"2022-07-28","cited_by_count":400},{"id":"1712.09867","title":"Future Frame Prediction for Anomaly Detection -- A New Baseline","created":"2017-12-28","cited_by_count":391},{"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":"1903.02741","title":"RAVEN: A Dataset for Relational and Analogical Visual rEasoNing","created":"2019-03-07","cited_by_count":226},{"id":"2104.10036","title":"VT-ADL: A Vision Transformer Network for Image Anomaly Detection and Localization","created":"2021-04-20","cited_by_count":223},{"id":"2112.09045","title":"The MVTec 3D-AD Dataset for Unsupervised 3D Anomaly Detection and Localization","created":"2021-12-16","cited_by_count":178},{"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":"2303.00601","title":"Multimodal Industrial Anomaly Detection via Hybrid Fusion","created":"2023-03-01","cited_by_count":139},{"id":"2403.12580","title":"Real-IAD: A Real-World Multi-View Dataset for Benchmarking Versatile Industrial Anomaly Detection","created":"2024-03-19","cited_by_count":139},{"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":"2308.11681","title":"VadCLIP: Adapting Vision-Language Models for Weakly Supervised Video Anomaly Detection","created":"2023-08-22","cited_by_count":123},{"id":"2203.03962","title":"Generative Cooperative Learning for Unsupervised Video Anomaly Detection","created":"2022-03-08","cited_by_count":102},{"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":"2309.13226","title":"Real3D-AD: A Dataset of Point Cloud Anomaly Detection","created":"2023-09-23","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":"1909.12000","title":"CoPhy: Counterfactual Learning of Physical Dynamics","created":"2019-09-26","cited_by_count":81},{"id":"2104.06689","title":"Learning Normal Dynamics in Videos with Meta Prototype Network","created":"2021-04-14","cited_by_count":71},{"id":"2401.16402","title":"A Survey on Visual Anomaly Detection: Challenge, Approach, and Prospect","created":"2024-01-29","cited_by_count":69},{"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":"2311.14897","title":"Towards Scalable 3D Anomaly Detection and Localization: A Benchmark via 3D Anomaly Synthesis and A Self-Supervised Learning Network","created":"2023-11-25","cited_by_count":67},{"id":"2303.12369","title":"Unbiased Multiple Instance Learning for Weakly Supervised Video Anomaly Detection","created":"2023-03-22","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":"2010.00763","title":"Bongard-LOGO: A New Benchmark for Human-Level Concept Learning and Reasoning","created":"2020-10-02","cited_by_count":63},{"id":"2210.04570","title":"The Eyecandies Dataset for Unsupervised Multimodal Anomaly Detection and Localization","created":"2022-10-10","cited_by_count":57},{"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":"2310.07716","title":"PAD: A Dataset and Benchmark for Pose-agnostic Anomaly Detection","created":"2023-10-11","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":"2206.05379","title":"A Benchmark for Compositional Visual Reasoning","created":"2022-06-11","cited_by_count":43},{"id":"2306.14451","title":"Learning Prompt-Enhanced Context Features for Weakly-Supervised Video Anomaly Detection","created":"2023-06-26","cited_by_count":43},{"id":"2205.13803","title":"Bongard-HOI: Benchmarking Few-Shot Visual Reasoning for Human-Object Interactions","created":"2022-05-27","cited_by_count":34},{"id":"2211.00882","title":"DyAnNet: A Scene Dynamicity Guided Self-Trained Video Anomaly Detection Network","created":"2022-11-02","cited_by_count":26},{"id":"2403.11083","title":"Customizing Visual-Language Foundation Models for Multi-modal Anomaly Detection and Reasoning","created":"2024-03-17","cited_by_count":20},{"id":"2406.04687","title":"LogiCode: an LLM-Driven Framework for Logical Anomaly Detection","created":"2024-06-07","cited_by_count":19},{"id":"1901.10364","title":"Anomaly Locality in Video Surveillance","created":"2019-01-29","cited_by_count":18},{"id":"2202.00368","title":"Filtered-CoPhy: Unsupervised Learning of Counterfactual Physics in Pixel Space","created":"2022-02-01","cited_by_count":14},{"id":"2108.06180","title":"SPACE: A Simulator for Physical Interactions and Causal Learning in 3D Environments","created":"2021-08-13","cited_by_count":9},{"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}