{"total":95,"rows":[{"id":"2106.10271","title":"End-to-end Temporal Action Detection with Transformer","created":"2021-06-18","cited_by_count":151,"area":null},{"id":"2104.01633","title":"MIST: Multiple Instance Self-Training Framework for Video Anomaly Detection","created":"2021-04-04","cited_by_count":138,"area":null},{"id":"2302.05160","title":"Dual Memory Units with Uncertainty Regulation for Weakly Supervised Video Anomaly Detection","created":"2023-02-10","cited_by_count":90,"area":null},{"id":"2104.07918","title":"Weakly Supervised Object Localization and Detection: A Survey","created":"2021-04-16","cited_by_count":84,"area":null},{"id":"2103.16392","title":"CoLA: Weakly-Supervised Temporal Action Localization with Snippet Contrastive Learning","created":"2021-03-30","cited_by_count":69,"area":null},{"id":"2101.00545","title":"A Hybrid Attention Mechanism for Weakly-Supervised Temporal Action Localization","created":"2021-01-03","cited_by_count":45,"area":null},{"id":"2108.05029","title":"Learning Action Completeness from Points for Weakly-supervised Temporal Action Localization","created":"2021-08-11","cited_by_count":42,"area":null},{"id":"2203.15187","title":"ASM-Loc: Action-aware Segment Modeling for Weakly-Supervised Temporal Action Localization","created":"2022-03-29","cited_by_count":40,"area":null},{"id":"2108.11996","title":"Drop-DTW: Aligning Common Signal Between Sequences While Dropping Outliers","created":"2021-08-26","cited_by_count":39,"area":null},{"id":"2111.12374","title":"MM-Pyramid: Multimodal Pyramid Attentional Network for Audio-Visual Event Localization and Video Parsing","created":"2021-11-24","cited_by_count":39,"area":null},{"id":"2106.16136","title":"Weakly Supervised Temporal Adjacent Network for Language Grounding","created":"2021-06-30","cited_by_count":37,"area":null},{"id":"2109.02613","title":"Class Semantics-based Attention for Action Detection","created":"2021-09-06","cited_by_count":36,"area":null},{"id":"2105.02668","title":"VideoLT: Large-scale Long-tailed Video Recognition","created":"2021-05-06","cited_by_count":35,"area":null},{"id":"2107.12589","title":"Cross-modal Consensus Network for Weakly Supervised Temporal Action Localization","created":"2021-07-27","cited_by_count":34,"area":null},{"id":"2203.16800","title":"Fine-grained Temporal Contrastive Learning for Weakly-supervised Temporal Action Localization","created":"2022-03-31","cited_by_count":33,"area":null},{"id":"2110.00111","title":"Deep Learning-based Action Detection in Untrimmed Videos: A Survey","created":"2021-09-30","cited_by_count":32,"area":null},{"id":"2203.02925","title":"Weakly Supervised Temporal Action Localization via Representative Snippet Knowledge Propagation","created":"2022-03-06","cited_by_count":32,"area":null},{"id":"2203.13609","title":"Unsupervised Pre-training for Temporal Action Localization Tasks","created":"2022-03-25","cited_by_count":31,"area":null},{"id":"2204.11573","title":"Joint-Modal Label Denoising for Weakly-Supervised Audio-Visual Video Parsing","created":"2022-04-25","cited_by_count":29,"area":null},{"id":"2104.14135","title":"Action Unit Memory Network for Weakly Supervised Temporal Action Localization","created":"2021-04-29","cited_by_count":26,"area":null},{"id":"2108.06524","title":"Foreground-Action Consistency Network for Weakly Supervised Temporal Action Localization","created":"2021-08-14","cited_by_count":26,"area":null},{"id":"2303.12332","title":"Weakly-Supervised Temporal Action Localization by Inferring Salient Snippet-Feature","created":"2023-03-22","cited_by_count":22,"area":null},{"id":"2105.02439","title":"Weakly Supervised Action Selection Learning in Video","created":"2021-05-06","cited_by_count":21,"area":null},{"id":"2111.12449","title":"Background-Click Supervision for Temporal Action Localization","created":"2021-11-24","cited_by_count":21,"area":null},{"id":"2103.15088","title":"ACSNet: Action-Context Separation Network for Weakly Supervised Temporal Action Localization","created":"2021-03-28","cited_by_count":20,"area":null},{"id":"2305.17861","title":"Proposal-Based Multiple Instance Learning for Weakly-Supervised Temporal Action Localization","created":"2023-05-29","cited_by_count":20,"area":null},{"id":"2104.02967","title":"ACM-Net: Action Context Modeling Network for Weakly-Supervised Temporal Action Localization","created":"2021-04-07","cited_by_count":19,"area":null},{"id":"2203.09338","title":"Object Localization under Single Coarse Point Supervision","created":"2022-03-17","cited_by_count":19,"area":null},{"id":"2303.11732","title":"Multi-modal Prompting for Low-Shot Temporal Action Localization","created":"2023-03-21","cited_by_count":19,"area":null},{"id":"2104.02357","title":"Adaptive Mutual Supervision for Weakly-Supervised Temporal Action Localization","created":"2021-04-06","cited_by_count":18,"area":null},{"id":"2112.10977","title":"ACGNet: Action Complement Graph Network for Weakly-supervised Temporal Action Localization","created":"2021-12-21","cited_by_count":17,"area":null},{"id":"2103.13183","title":"The Blessings of Unlabeled Background in Untrimmed Videos","created":"2021-03-24","cited_by_count":16,"area":null},{"id":"2304.07978","title":"Improving Weakly Supervised Temporal Action Localization by Bridging Train-Test Gap in Pseudo Labels","created":"2023-04-17","cited_by_count":14,"area":null},{"id":"2202.08199","title":"Less is More: Surgical Phase Recognition from Timestamp Supervision","created":"2022-02-16","cited_by_count":13,"area":null},{"id":"2103.11671","title":"Unsupervised Two-Stage Anomaly Detection","created":"2021-03-22","cited_by_count":12,"area":null},{"id":"2103.16155","title":"Weakly Supervised Temporal Action Localization Through Learning Explicit Subspaces for Action and Context","created":"2021-03-30","cited_by_count":12,"area":null},{"id":"2110.05697","title":"Hierarchical Modeling for Task Recognition and Action Segmentation in Weakly-Labeled Instructional Videos","created":"2021-10-12","cited_by_count":11,"area":null},{"id":"2210.07548","title":"Reconstructed Student-Teacher and Discriminative Networks for Anomaly Detection","created":"2022-10-14","cited_by_count":11,"area":null},{"id":"2208.01954","title":"Dilated Context Integrated Network with Cross-Modal Consensus for Temporal Emotion Localization in Videos","created":"2022-08-03","cited_by_count":10,"area":null},{"id":"2208.05251","title":"Consistency-based Self-supervised Learning for Temporal Anomaly Localization","created":"2022-08-10","cited_by_count":10,"area":null},{"id":"2308.07795","title":"Learning to Identify Critical States for Reinforcement Learning from Videos","created":"2023-08-15","cited_by_count":9,"area":null},{"id":"2207.11805","title":"Weakly-Supervised Temporal Action Detection for Fine-Grained Videos with Hierarchical Atomic Actions","created":"2022-07-24","cited_by_count":8,"area":null},{"id":"2303.06378","title":"Learning Grounded Vision-Language Representation for Versatile Understanding in Untrimmed Videos","created":"2023-03-11","cited_by_count":8,"area":null},{"id":"2305.00607","title":"Boosting Weakly-Supervised Temporal Action Localization with Text Information","created":"2023-05-01","cited_by_count":8,"area":null},{"id":"2312.14138","title":"Revisiting Foreground and Background Separation in Weakly-supervised Temporal Action Localization: A Clustering-based Approach","created":"2023-12-21","cited_by_count":8,"area":null},{"id":"2108.05607","title":"Deep Motion Prior for Weakly-Supervised Temporal Action Localization","created":"2021-08-12","cited_by_count":7,"area":null},{"id":"2307.16415","title":"DDG-Net: Discriminability-Driven Graph Network for Weakly-supervised Temporal Action Localization","created":"2023-07-31","cited_by_count":7,"area":null},{"id":"2111.13675","title":"Weakly-guided Self-supervised Pretraining for Temporal Activity Detection","created":"2021-11-26","cited_by_count":5,"area":null},{"id":"2206.11011","title":"Weakly-Supervised Temporal Action Localization by Progressive Complementary Learning","created":"2022-06-22","cited_by_count":5,"area":null},{"id":"2206.13502","title":"Programmatic Concept Learning for Human Motion Description and Synthesis","created":"2022-06-27","cited_by_count":5,"area":null},{"id":"2412.21205","title":"Action-Agnostic Point-Level Supervision for Temporal Action Detection","created":"2024-12-30","cited_by_count":5,"area":null},{"id":"2104.06653","title":"ADNet: Temporal Anomaly Detection in Surveillance Videos","created":"2021-04-14","cited_by_count":4,"area":null},{"id":"2106.11811","title":"Weakly-Supervised Temporal Action Localization Through Local-Global Background Modeling","created":"2021-06-20","cited_by_count":4,"area":null},{"id":"2108.11149","title":"A Unified Taxonomy and Multimodal Dataset for Events in Invasion Games","created":"2021-08-25","cited_by_count":4,"area":null},{"id":"2207.06659","title":"Forcing the Whole Video as Background: An Adversarial Learning Strategy for Weakly Temporal Action Localization","created":"2022-07-14","cited_by_count":4,"area":null},{"id":"2211.11324","title":"Slow Motion Matters: A Slow Motion Enhanced Network for Weakly Supervised Temporal Action Localization","created":"2022-11-21","cited_by_count":4,"area":null},{"id":"2305.02734","title":"Weakly-supervised Micro- and Macro-expression Spotting Based on Multi-level Consistency","created":"2023-05-04","cited_by_count":4,"area":null},{"id":"2308.09946","title":"Weakly-Supervised Action Localization by Hierarchically-structured Latent Attention Modeling","created":"2023-08-19","cited_by_count":4,"area":null},{"id":"2308.12609","title":"Cross-Video Contextual Knowledge Exploration and Exploitation for Ambiguity Reduction in Weakly Supervised Temporal Action Localization","created":"2023-08-24","cited_by_count":4,"area":null},{"id":"2404.13311","title":"STAT: Towards Generalizable Temporal Action Localization","created":"2024-04-20","cited_by_count":4,"area":null},{"id":"2104.14124","title":"Condensation-Net: Memory-Efficient Network Architecture with Cross-Channel Pooling Layers and Virtual Feature Maps","created":"2021-04-29","cited_by_count":3,"area":null},{"id":"2211.17071","title":"Interpreting Vulnerabilities of Multi-Instance Learning to Adversarial Perturbations","created":"2022-11-30","cited_by_count":3,"area":null},{"id":"2312.07384","title":"Visual Self-paced Iterative Learning for Unsupervised Temporal Action Localization","created":"2023-12-12","cited_by_count":3,"area":null},{"id":"2408.05955","title":"Probabilistic Vision-Language Representation for Weakly Supervised Temporal Action Localization","created":"2024-08-12","cited_by_count":3,"area":null},{"id":"2105.10313","title":"Sharing Pain: Using Pain Domain Transfer for Video Recognition of Low Grade Orthopedic Pain in Horses","created":"2021-05-21","cited_by_count":2,"area":null},{"id":"2108.13258","title":"Equine Pain Behavior Classification via Self-Supervised Disentangled Pose Representation","created":"2021-08-30","cited_by_count":2,"area":null},{"id":"2110.08708","title":"Robust Pedestrian Attribute Recognition Using Group Sparsity for Occlusion Videos","created":"2021-10-17","cited_by_count":2,"area":null},{"id":"2205.00400","title":"Convex Combination Consistency between Neighbors for Weakly-supervised Action Localization","created":"2022-05-01","cited_by_count":2,"area":null},{"id":"2304.12616","title":"Weakly-Supervised Temporal Action Localization with Bidirectional Semantic Consistency Constraint","created":"2023-04-25","cited_by_count":2,"area":null},{"id":"2402.06107","title":"Multiple Instance Learning for Cheating Detection and Localization in Online Examinations","created":"2024-02-09","cited_by_count":2,"area":null},{"id":"2403.14240","title":"Weak Supervision with Arbitrary Single Frame for Micro- and Macro-expression Spotting","created":"2024-03-21","cited_by_count":2,"area":null},{"id":"2505.23524","title":"CLIP-AE: CLIP-assisted Cross-view Audio-Visual Enhancement for Unsupervised Temporal Action Localization","created":"2025-05-29","cited_by_count":2,"area":null},{"id":"2506.17516","title":"EASE: Embodied Active Event Perception via Self-Supervised Energy Minimization","created":"2025-06-20","cited_by_count":2,"area":null},{"id":"2605.25409","title":"MTLLFM: Multimodal-Temporal Laughter Localization: UR-FUNNY-Temporal and SMILE-Temporal Benchmarks with an Adaptive Multimodal Fusion Model","created":"2026-05-25","cited_by_count":2,"area":null},{"id":"2110.09110","title":"Graph Convolution Neural Network For Weakly Supervised Abnormality Localization In Long Capsule Endoscopy Videos","created":"2021-10-18","cited_by_count":1,"area":null},{"id":"2401.17203","title":"CPR++: Object Localization via Single Coarse Point Supervision","created":"2024-01-30","cited_by_count":1,"area":null},{"id":"2508.03397","title":"DepthGait: Multi-Scale Cross-Level Feature Fusion of RGB-Derived Depth and Silhouette Sequences for Robust Gait Recognition","created":"2025-08-05","cited_by_count":1,"area":null},{"id":"2603.14750","title":"Face-Guided Sentiment Boundary Enhancement for Weakly-Supervised Temporal Sentiment Localization","created":"2026-03-16","cited_by_count":1,"area":null},{"id":"2105.04208","title":"Action Shuffling for Weakly Supervised Temporal Localization","created":"2021-05-10","cited_by_count":0,"area":null},{"id":"2105.14430","title":"Rethinking the constraints of multimodal fusion: case study in Weakly-Supervised Audio-Visual Video Parsing","created":"2021-05-30","cited_by_count":0,"area":null},{"id":"2106.04150","title":"Few-Shot Action Localization without Knowing Boundaries","created":"2021-06-08","cited_by_count":0,"area":null},{"id":"2110.09060","title":"Discovery-and-Selection: Towards Optimal Multiple Instance Learning for Weakly Supervised Object Detection","created":"2021-10-18","cited_by_count":0,"area":null},{"id":"2205.05895","title":"Weakly-Supervised Action Detection Guided by Audio Narration","created":"2022-05-12","cited_by_count":0,"area":null},{"id":"2206.08429","title":"Scalable Temporal Localization of Sensitive Activities in Movies and TV Episodes","created":"2022-06-16","cited_by_count":0,"area":null},{"id":"2209.03609","title":"Frame-Subtitle Self-Supervision for Multi-Modal Video Question Answering","created":"2022-09-08","cited_by_count":0,"area":null},{"id":"2303.17294","title":"JCDNet: Joint of Common and Definite phases Network for Weakly Supervised Temporal Action Localization","created":"2023-03-30","cited_by_count":0,"area":null},{"id":"2305.04186","title":"Video-Specific Query-Key Attention Modeling for Weakly-Supervised Temporal Action Localization","created":"2023-05-07","cited_by_count":0,"area":null},{"id":"2307.06385","title":"Temporal Label-Refinement for Weakly-Supervised Audio-Visual Event Localization","created":"2023-07-12","cited_by_count":0,"area":null},{"id":"2308.09268","title":"Progression-Guided Temporal Action Detection in Videos","created":"2023-08-18","cited_by_count":0,"area":null},{"id":"2411.01527","title":"Performance Evaluation of Deep Learning Models for Water Quality Index Prediction: A Comparative Study of LSTM, TCN, ANN, and MLP","created":"2024-11-03","cited_by_count":0,"area":null},{"id":"2505.17555","title":"ProTAL: A Drag-and-Link Video Programming Framework for Temporal Action Localization","created":"2025-05-23","cited_by_count":0,"area":null},{"id":"2506.18261","title":"Improving Weakly Supervised Temporal Action Localization by Exploiting Multi-resolution Information in Temporal Domain","created":"2025-06-23","cited_by_count":0,"area":null},{"id":"2511.13039","title":"MGCA-Net: Multi-Grained Category-Aware Network for Open-Vocabulary Temporal Action Localization","created":"2025-11-17","cited_by_count":0,"area":null},{"id":"2602.01850","title":"WS-IMUBench: Can Weakly Supervised Methods from Audio, Image, and Video Be Adapted for IMU-based Temporal Action Localization?","created":"2026-02-02","cited_by_count":0,"area":null},{"id":"2608.25344","title":"CoRE: Weakly Supervised Coarse-to-Fine Risk Evidence Learning in Driving Videos","created":"2026-08-26","cited_by_count":0,"area":null}],"next_cursor":null}