{"list":"other","total":141,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"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":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"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":"2408.03326","title":"LLaVA-OneVision: Easy Visual Task Transfer","created":"2024-08-06","cited_by_count":2719},{"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":"2406.12793","title":"ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools","created":"2024-06-18","cited_by_count":1121},{"id":"2106.13230","title":"Video Swin Transformer","created":"2021-06-24","cited_by_count":1091},{"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":"2303.15389","title":"EVA-CLIP: Improved Training Techniques for CLIP at Scale","created":"2023-03-27","cited_by_count":798},{"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":"1711.09577","title":"Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?","created":"2017-11-27","cited_by_count":551},{"id":"2312.02051","title":"TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding","created":"2023-12-04","cited_by_count":406},{"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":"2311.18445","title":"VTimeLLM: Empower LLM to Grasp Video Moments","created":"2023-11-30","cited_by_count":255},{"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":"2101.10030","title":"Weakly-supervised Video Anomaly Detection with Robust Temporal Feature Magnitude Learning","created":"2021-01-25","cited_by_count":230},{"id":"1802.09088","title":"Adversarially Learned One-Class Classifier for Novelty Detection","created":"2018-02-25","cited_by_count":202},{"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":"2011.07491","title":"Anomaly Detection in Video via Self-Supervised and Multi-Task Learning","created":"2020-11-15","cited_by_count":148},{"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":"2007.01760","title":"Explainable Deep One-Class Classification","created":"2020-07-03","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":"1908.06351","title":"Anomaly Detection in Video Sequence with Appearance-Motion Correspondence","created":"2019-08-17","cited_by_count":118},{"id":"2004.07657","title":"Old is Gold: Redefining the Adversarially Learned One-Class Classifier Training Paradigm","created":"2020-04-16","cited_by_count":115},{"id":"1812.04960","title":"Object-centric Auto-encoders and Dummy Anomalies for Abnormal Event Detection in Video","created":"2018-12-11","cited_by_count":111},{"id":"1903.03295","title":"Learning Regularity in Skeleton Trajectories for Anomaly Detection in Videos","created":"2019-03-08","cited_by_count":104},{"id":"2203.14506","title":"Catching Both Gray and Black Swans: Open-set Supervised Anomaly Detection","created":"2022-03-28","cited_by_count":104},{"id":"2203.03962","title":"Generative Cooperative Learning for Unsupervised Video Anomaly Detection","created":"2022-03-08","cited_by_count":102},{"id":"2111.08644","title":"UBnormal: New Benchmark for Supervised Open-Set Video Anomaly Detection","created":"2021-11-16","cited_by_count":93},{"id":"1902.05872","title":"Street Scene: A new dataset and evaluation protocol for video anomaly detection","created":"2019-02-15","cited_by_count":90},{"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":"2004.05993","title":"A Survey of Single-Scene Video Anomaly Detection","created":"2020-04-13","cited_by_count":88},{"id":"2404.01014","title":"Harnessing Large Language Models for Training-free Video Anomaly Detection","created":"2024-04-01","cited_by_count":87},{"id":"2008.12328","title":"A Background-Agnostic Framework with Adversarial Training for Abnormal Event Detection in Video","created":"2020-08-27","cited_by_count":86},{"id":"2003.06780","title":"Self-trained Deep Ordinal Regression for End-to-End Video Anomaly Detection","created":"2020-03-15","cited_by_count":83},{"id":"1708.09644","title":"Abnormal Event Detection in Videos using Generative Adversarial Nets","created":"2017-08-31","cited_by_count":82},{"id":"2011.12077","title":"CLAWS: Clustering Assisted Weakly Supervised Learning with Normalcy Suppression for Anomalous Event Detection","created":"2020-11-24","cited_by_count":79},{"id":"1510.01553","title":"Learning Deep Representations of Appearance and Motion for Anomalous Event Detection","created":"2015-10-06","cited_by_count":75},{"id":"2104.06689","title":"Learning Normal Dynamics in Videos with Meta Prototype Network","created":"2021-04-14","cited_by_count":71},{"id":"2008.11988","title":"Cloze Test Helps: Effective Video Anomaly Detection via Learning to Complete Video Events","created":"2020-08-27","cited_by_count":70},{"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":"2303.12369","title":"Unbiased Multiple Instance Learning for Weakly Supervised Video Anomaly Detection","created":"2023-03-22","cited_by_count":64},{"id":"2007.07843","title":"Few-shot Scene-adaptive Anomaly Detection","created":"2020-07-15","cited_by_count":62},{"id":"2207.10172","title":"Video Anomaly Detection by Solving Decoupled Spatio-Temporal Jigsaw Puzzles","created":"2022-07-20","cited_by_count":62},{"id":"2211.10946","title":"Normalizing Flows for Human Pose Anomaly Detection","created":"2022-11-20","cited_by_count":60},{"id":"1908.04321","title":"Multi-timescale Trajectory Prediction for Abnormal Human Activity Detection","created":"2019-08-12","cited_by_count":59},{"id":"2302.05087","title":"Generalized Video Anomaly Event Detection: Systematic Taxonomy and Comparison of Deep Models","created":"2023-02-10","cited_by_count":59},{"id":"2311.07042","title":"Open-Vocabulary Video Anomaly Detection","created":"2023-11-13","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":"1709.09121","title":"Joint Detection and Recounting of Abnormal Events by Learning Deep Generic Knowledge","created":"2017-09-26","cited_by_count":55},{"id":"2212.09522","title":"MIST: Multi-modal Iterative Spatial-Temporal Transformer for Long-form Video Question Answering","created":"2022-12-19","cited_by_count":55},{"id":"2304.05112","title":"Video Event Restoration Based on Keyframes for Video Anomaly Detection","created":"2023-04-11","cited_by_count":54},{"id":"1609.00866","title":"Deep-Anomaly: Fully Convolutional Neural Network for Fast Anomaly Detection in Crowded Scenes","created":"2016-09-03","cited_by_count":50},{"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":"1705.08182","title":"Unmasking the abnormal events in video","created":"2017-05-23","cited_by_count":48},{"id":"1907.10211","title":"Motion-Aware Feature for Improved Video Anomaly Detection","created":"2019-07-24","cited_by_count":48},{"id":"2212.04090","title":"Exploiting Completeness and Uncertainty of Pseudo Labels for Weakly Supervised Video Anomaly Detection","created":"2022-12-08","cited_by_count":47},{"id":"2401.05702","title":"Video Anomaly Detection and Explanation via Large Language Models","created":"2024-01-11","cited_by_count":47},{"id":"2207.08003","title":"SSMTL++: Revisiting Self-Supervised Multi-Task Learning for Video Anomaly Detection","created":"2022-07-16","cited_by_count":45},{"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":"2104.07268","title":"Weakly Supervised Video Anomaly Detection via Center-guided Discriminative Learning","created":"2021-04-15","cited_by_count":44},{"id":"2306.14451","title":"Learning Prompt-Enhanced Context Features for Weakly-Supervised Video Anomaly Detection","created":"2023-06-26","cited_by_count":43},{"id":"2006.11629","title":"G2D: Generate to Detect Anomaly","created":"2020-06-20","cited_by_count":42},{"id":"2011.02763","title":"Robust Unsupervised Video Anomaly Detection by Multi-Path Frame Prediction","created":"2020-11-05","cited_by_count":42},{"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":"2307.07205","title":"Multimodal Motion Conditioned Diffusion Model for Skeleton-based Video Anomaly Detection","created":"2023-07-14","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":"2408.05905","title":"Weakly Supervised Video Anomaly Detection and Localization with Spatio-Temporal Prompts","created":"2024-08-12","cited_by_count":40},{"id":"2303.13051","title":"Hierarchical Semantic Contrast for Scene-aware Video Anomaly Detection","created":"2023-03-23","cited_by_count":39},{"id":"2306.12041","title":"Self-Distilled Masked Auto-Encoders are Efficient Video Anomaly Detectors","created":"2023-06-21","cited_by_count":37},{"id":"2001.09189","title":"Learning a distance function with a Siamese network to localize anomalies in videos","created":"2020-01-24","cited_by_count":31},{"id":"2107.13720","title":"Convolutional Transformer based Dual Discriminator Generative Adversarial Networks for Video Anomaly Detection","created":"2021-07-29","cited_by_count":31},{"id":"2110.09742","title":"Learning Not to Reconstruct Anomalies","created":"2021-10-19","cited_by_count":31},{"id":"1706.07680","title":"Training Adversarial Discriminators for Cross-channel Abnormal Event Detection in Crowds","created":"2017-06-23","cited_by_count":28},{"id":"2112.04294","title":"A Hierarchical Spatio-Temporal Graph Convolutional Neural Network for Anomaly Detection in Videos","created":"2021-12-08","cited_by_count":28},{"id":"2004.03044","title":"When, Where, and What? A New Dataset for Anomaly Detection in Driving Videos","created":"2020-04-06","cited_by_count":27},{"id":"2207.10948","title":"Dynamic Local Aggregation Network with Adaptive Clusterer for Anomaly Detection","created":"2022-07-22","cited_by_count":27},{"id":"2310.02835","title":"Delving into CLIP latent space for Video Anomaly Recognition","created":"2023-10-04","cited_by_count":27},{"id":"2409.05383","title":"Deep Learning for Video Anomaly Detection: A Review","created":"2024-09-09","cited_by_count":27},{"id":"2207.05500","title":"Modality-Aware Contrastive Instance Learning with Self-Distillation for Weakly-Supervised Audio-Visual Violence Detection","created":"2022-07-12","cited_by_count":26},{"id":"2208.11113","title":"Towards Open Set Video Anomaly Detection","created":"2022-08-23","cited_by_count":26},{"id":"2310.12790","title":"Anomaly Heterogeneity Learning for Open-set Supervised Anomaly Detection","created":"2023-10-19","cited_by_count":25},{"id":"1612.00390","title":"Anomaly Detection in Video Using Predictive Convolutional Long Short-Term Memory Networks","created":"2016-12-01","cited_by_count":24},{"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":"2308.11072","title":"TeD-SPAD: Temporal Distinctiveness for Self-supervised Privacy-preservation for video Anomaly Detection","created":"2023-08-21","cited_by_count":23},{"id":"2112.03649","title":"Regularity Learning via Explicit Distribution Modeling for Skeletal Video Anomaly Detection","created":"2021-12-07","cited_by_count":22},{"id":"2302.04549","title":"Weakly Supervised Anomaly Detection: A Survey","created":"2023-02-09","cited_by_count":22}],"next_cursor":"100"}