{"list":"other","total":56,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2102.05918","title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision","created":"2021-02-11","cited_by_count":3864},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"2109.01134","title":"Learning to Prompt for Vision-Language Models","created":"2021-09-02","cited_by_count":2281},{"id":"2203.12602","title":"VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training","created":"2022-03-23","cited_by_count":1322},{"id":"2305.06355","title":"VideoChat: Chat-Centric Video Understanding","created":"2023-05-10","cited_by_count":857},{"id":"2109.14084","title":"VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding","created":"2021-09-28","cited_by_count":602},{"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":"2102.02779","title":"Unifying Vision-and-Language Tasks via Text Generation","created":"2021-02-04","cited_by_count":412},{"id":"1712.09867","title":"Future Frame Prediction for Anomaly Detection -- A New Baseline","created":"2017-12-28","cited_by_count":391},{"id":"2208.02816","title":"Expanding Language-Image Pretrained Models for General Video Recognition","created":"2022-08-04","cited_by_count":321},{"id":"2112.04478","title":"Prompting Visual-Language Models for Efficient Video Understanding","created":"2021-12-08","cited_by_count":310},{"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":"2110.11499","title":"Wav2CLIP: Learning Robust Audio Representations From CLIP","created":"2021-10-21","cited_by_count":213},{"id":"1608.08242","title":"Temporal Convolutional Networks: A Unified Approach to Action Segmentation","created":"2016-08-29","cited_by_count":199},{"id":"2203.14072","title":"Learning to Answer Questions in Dynamic Audio-Visual Scenarios","created":"2022-03-26","cited_by_count":191},{"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":"2202.09061","title":"VLP: A Survey on Vision-Language Pre-training","created":"2022-02-18","cited_by_count":159},{"id":"2007.10558","title":"Unified Multisensory Perception: Weakly-Supervised Audio-Visual Video Parsing","created":"2020-07-21","cited_by_count":146},{"id":"2104.01633","title":"MIST: Multiple Instance Self-Training Framework for Video Anomaly Detection","created":"2021-04-04","cited_by_count":138},{"id":"1712.09763","title":"PixelSNAIL: An Improved Autoregressive Generative Model","created":"2017-12-28","cited_by_count":137},{"id":"2003.11339","title":"Data Uncertainty Learning in Face Recognition","created":"2020-03-25","cited_by_count":134},{"id":"2308.11681","title":"VadCLIP: Adapting Vision-Language Models for Weakly Supervised Video Anomaly Detection","created":"2023-08-22","cited_by_count":123},{"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":"1807.10418","title":"W-TALC: Weakly-supervised Temporal Activity Localization and Classification","created":"2018-07-27","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":"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":"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":"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":"2311.07042","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":"2304.05112","title":"Video Event Restoration Based on Keyframes for Video Anomaly Detection","created":"2023-04-11","cited_by_count":54},{"id":"2008.08944","title":"Localizing Anomalies from Weakly-Labeled Videos","created":"2020-08-20","cited_by_count":52},{"id":"2404.08531","title":"Text Prompt with Normality Guidance for Weakly Supervised Video Anomaly Detection","created":"2024-04-12","cited_by_count":49},{"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":"2208.09579","title":"Learning in Audio-visual Context: A Review, Analysis, and New Perspective","created":"2022-08-20","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":"2408.05905","title":"Weakly Supervised Video Anomaly Detection and Localization with Spatio-Temporal Prompts","created":"2024-08-12","cited_by_count":40},{"id":"2304.02970","title":"Unraveling Instance Associations: A Closer Look for Audio-Visual Segmentation","created":"2023-04-06","cited_by_count":34},{"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":"2307.12545","title":"Towards Video Anomaly Retrieval from Video Anomaly Detection: New Benchmarks and Model","created":"2023-07-24","cited_by_count":25},{"id":"2407.08126","title":"Label-anticipated Event Disentanglement for Audio-Visual Video Parsing","created":"2024-07-11","cited_by_count":25},{"id":"2407.11820","title":"Stepping Stones: A Progressive Training Strategy for Audio-Visual Semantic Segmentation","created":"2024-07-16","cited_by_count":23},{"id":"2410.01506","title":"Learnable Expansion of Graph Operators for Multi-Modal Feature Fusion","created":"2024-10-02","cited_by_count":23},{"id":"2406.00919","title":"Advancing Weakly-Supervised Audio-Visual Video Parsing via Segment-wise Pseudo Labeling","created":"2024-06-03","cited_by_count":20},{"id":"2209.02899","title":"Context Recovery and Knowledge Retrieval: A Novel Two-Stream Framework for Video Anomaly Detection","created":"2022-09-07","cited_by_count":18},{"id":"2407.21721","title":"Open-Vocabulary Audio-Visual Semantic Segmentation","created":"2024-07-31","cited_by_count":16},{"id":"2404.05559","title":"TIM: A Time Interval Machine for Audio-Visual Action Recognition","created":"2024-04-08","cited_by_count":15},{"id":"2203.13716","title":"Stabilizing Adversarially Learned One-Class Novelty Detection Using Pseudo Anomalies","created":"2022-03-25","cited_by_count":14},{"id":"2408.01952","title":"CACE-Net: Co-guidance Attention and Contrastive Enhancement for Effective Audio-Visual Event Localization","created":"2024-08-04","cited_by_count":10},{"id":"2409.19252","title":"Beyond Euclidean: Dual-Space Representation Learning for Weakly Supervised Video Violence Detection","created":"2024-09-28","cited_by_count":10}],"next_cursor":null}