{"total":82,"rows":[{"id":"2106.10271","title":"End-to-end Temporal Action Detection with Transformer","created":"2021-06-18","cited_by_count":151,"area":null},{"id":"2303.07347","title":"TriDet: Temporal Action Detection with Relative Boundary Modeling","created":"2023-03-13","cited_by_count":142,"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":"2104.07268","title":"Weakly Supervised Video Anomaly Detection via Center-guided Discriminative Learning","created":"2021-04-15","cited_by_count":44,"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":"2109.02613","title":"Class Semantics-based Attention for Action Detection","created":"2021-09-06","cited_by_count":36,"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":"2107.12059","title":"HANet: Hierarchical Alignment Networks for Video-Text Retrieval","created":"2021-07-26","cited_by_count":31,"area":null},{"id":"2108.10576","title":"Support-Set Based Cross-Supervision for Video Grounding","created":"2021-08-24","cited_by_count":28,"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":"2307.12545","title":"Towards Video Anomaly Retrieval from Video Anomaly Detection: New Benchmarks and Model","created":"2023-07-24","cited_by_count":25,"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":"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":"2309.16309","title":"Weakly-Supervised Video Anomaly Detection with Snippet Anomalous Attention","created":"2023-09-28","cited_by_count":15,"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":"2104.08030","title":"Temporally smooth online action detection using cycle-consistent future anticipation","created":"2021-04-16","cited_by_count":13,"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":"2309.05590","title":"Temporal Action Localization with Enhanced Instant Discriminability","created":"2023-09-11","cited_by_count":13,"area":null},{"id":"2310.05241","title":"SCANet: Scene Complexity Aware Network for Weakly-Supervised Video Moment Retrieval","created":"2023-10-08","cited_by_count":13,"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":"2412.20455","title":"Cross-Modal Fusion and Attention Mechanism for Weakly Supervised Video Anomaly Detection","created":"2024-12-29","cited_by_count":10,"area":null},{"id":"2104.02113","title":"Anchor-Constrained Viterbi for Set-Supervised Action Segmentation","created":"2021-04-05","cited_by_count":8,"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":"2208.05636","title":"Locality-aware Attention Network with Discriminative Dynamics Learning for Weakly Supervised Anomaly Detection","created":"2022-08-11","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":"2202.06503","title":"Adaptive Graph Convolutional Networks for Weakly Supervised Anomaly Detection in Videos","created":"2022-02-14","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":"2504.04495","title":"AVadCLIP: Audio-Visual Collaboration for Robust Video Anomaly Detection","created":"2025-04-06","cited_by_count":7,"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":"2412.21205","title":"Action-Agnostic Point-Level Supervision for Temporal Action Detection","created":"2024-12-30","cited_by_count":5,"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":"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":"2306.06823","title":"Weakly supervised information extraction from inscrutable handwritten document images","created":"2023-06-12","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":"2201.00434","title":"TVNet: Temporal Voting Network for Action Localization","created":"2022-01-02","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":"2407.08971","title":"Full-Stage Pseudo Label Quality Enhancement for Weakly-supervised Temporal Action Localization","created":"2024-07-12","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":"2506.13095","title":"Learning Event Completeness for Weakly Supervised Video Anomaly Detection","created":"2025-06-16","cited_by_count":3,"area":null},{"id":"2603.00550","title":"Weakly Supervised Video Anomaly Detection with Anomaly-Connected Components and Intention Reasoning","created":"2026-02-28","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":"2208.03648","title":"Weakly Supervised Online Action Detection for Infant General Movements","created":"2022-08-07","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":"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":"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":"2309.09060","title":"Sub-action Prototype Learning for Point-level Weakly-supervised Temporal Action Localization","created":"2023-09-16","cited_by_count":1,"area":null},{"id":"2310.05330","title":"A Lightweight Video Anomaly Detection Model with Weak Supervision and Adaptive Instance Selection","created":"2023-10-09","cited_by_count":1,"area":null},{"id":"2410.00536","title":"Arges: Spatio-Temporal Transformer for Ulcerative Colitis Severity Assessment in Endoscopy Videos","created":"2024-10-01","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":"2204.13548","title":"Tragedy Plus Time: Capturing Unintended Human Activities from Weakly-labeled Videos","created":"2022-04-28","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":"2208.12673","title":"Enabling Weakly-Supervised Temporal Action Localization from On-Device Learning of the Video Stream","created":"2022-08-25","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":"2212.06348","title":"Dilation-Erosion for Single-Frame Supervised Temporal Action Localization","created":"2022-12-13","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":"2410.18695","title":"PESFormer: Boosting Macro- and Micro-expression Spotting with Direct Timestamp Encoding","created":"2024-10-24","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":"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}