{"total":130,"rows":[{"id":"2202.07925","title":"ActionFormer: Localizing Moments of Actions with Transformers","created":"2022-02-16","cited_by_count":311,"area":null},{"id":"2106.10271","title":"End-to-end Temporal Action Detection with Transformer","created":"2021-06-18","cited_by_count":151,"area":null},{"id":"2102.01894","title":"Relaxed Transformer Decoders for Direct Action Proposal Generation","created":"2021-02-03","cited_by_count":117,"area":null},{"id":"2103.13141","title":"Temporal Context Aggregation Network for Temporal Action Proposal Refinement","created":"2021-03-24","cited_by_count":112,"area":null},{"id":"2203.03962","title":"Generative Cooperative Learning for Unsupervised Video Anomaly Detection","created":"2022-03-08","cited_by_count":102,"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":"2203.09324","title":"Localizing Visual Sounds the Easy Way","created":"2022-03-17","cited_by_count":82,"area":null},{"id":"2209.09634","title":"A Closer Look at Weakly-Supervised Audio-Visual Source Localization","created":"2022-08-30","cited_by_count":73,"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":"2107.12960","title":"Enriching Local and Global Contexts for Temporal Action Localization","created":"2021-07-27","cited_by_count":64,"area":null},{"id":"2101.08540","title":"Activity Graph Transformer for Temporal Action Localization","created":"2021-01-21","cited_by_count":48,"area":null},{"id":"2207.07097","title":"ReAct: Temporal Action Detection with Relational Queries","created":"2022-07-14","cited_by_count":48,"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":"2104.03214","title":"Self-Supervised Learning for Semi-Supervised Temporal Action Proposal","created":"2021-04-07","cited_by_count":39,"area":null},{"id":"2406.06890","title":"Motion Consistency Model: Accelerating Video Diffusion with Disentangled Motion-Appearance Distillation","created":"2024-06-11","cited_by_count":39,"area":"diffusion"},{"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":"2112.03612","title":"DCAN: Improving Temporal Action Detection via Dual Context Aggregation","created":"2021-12-07","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":"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":"2112.00302","title":"Graph Convolutional Module for Temporal Action Localization in Videos","created":"2021-12-01","cited_by_count":29,"area":null},{"id":"2207.06580","title":"Proposal-Free Temporal Action Detection via Global Segmentation Mask Learning","created":"2022-07-14","cited_by_count":29,"area":null},{"id":"2205.02717","title":"BasicTAD: an Astounding RGB-Only Baseline for Temporal Action Detection","created":"2022-05-05","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":"2103.16024","title":"Augmented Transformer with Adaptive Graph for Temporal Action Proposal Generation","created":"2021-03-30","cited_by_count":25,"area":null},{"id":"2203.07112","title":"RCL: Recurrent Continuous Localization for Temporal Action Detection","created":"2022-03-14","cited_by_count":25,"area":null},{"id":"2212.11078","title":"C2F-TCN: A Framework for Semi and Fully Supervised Temporal Action Segmentation","created":"2022-12-20","cited_by_count":23,"area":null},{"id":"2309.01246","title":"Towards Generic Image Manipulation Detection with Weakly-Supervised Self-Consistency Learning","created":"2023-09-03","cited_by_count":23,"area":null},{"id":"2210.11035","title":"PointTAD: Multi-Label Temporal Action Detection with Learnable Query Points","created":"2022-10-20","cited_by_count":22,"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":"2306.07515","title":"A Survey on Video Moment Localization","created":"2023-06-13","cited_by_count":18,"area":null},{"id":"2105.12043","title":"Temporal Action Proposal Generation with Transformers","created":"2021-05-25","cited_by_count":17,"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":"2303.16891","title":"Mask-free OVIS: Open-Vocabulary Instance Segmentation without Manual Mask Annotations","created":"2023-03-29","cited_by_count":16,"area":"mllm"},{"id":"2308.12608","title":"HR-Pro: Point-supervised Temporal Action Localization via Hierarchical Reliability Propagation","created":"2023-08-24","cited_by_count":16,"area":null},{"id":"2110.10552","title":"Few-Shot Temporal Action Localization with Query Adaptive Transformer","created":"2021-10-20","cited_by_count":15,"area":null},{"id":"2210.02578","title":"AOE-Net: Entities Interactions Modeling with Adaptive Attention Mechanism for Temporal Action Proposals Generation","created":"2022-10-05","cited_by_count":14,"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":"2305.15699","title":"Cross-view Action Recognition Understanding From Exocentric to Egocentric Perspective","created":"2023-05-25","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":"2103.16155","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":"2203.13704","title":"Clustering Aided Weakly Supervised Training to Detect Anomalous Events in Surveillance Videos","created":"2022-03-25","cited_by_count":12,"area":null},{"id":"2212.09335","title":"Distilling Vision-Language Pre-training to Collaborate with Weakly-Supervised Temporal Action Localization","created":"2022-12-19","cited_by_count":12,"area":"mllm"},{"id":"2110.11474","title":"AEI: Actors-Environment Interaction with Adaptive Attention for Temporal Action Proposals Generation","created":"2021-10-21","cited_by_count":11,"area":null},{"id":"2204.02674","title":"Faster-TAD: Towards Temporal Action Detection with Proposal Generation and Classification in a Unified Network","created":"2022-04-06","cited_by_count":10,"area":null},{"id":"2205.07134","title":"ETAD: Training Action Detection End to End on a Laptop","created":"2022-05-14","cited_by_count":10,"area":null},{"id":"2207.07059","title":"Semi-Supervised Temporal Action Detection with Proposal-Free Masking","created":"2022-07-14","cited_by_count":10,"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":"2308.07050","title":"Survey on video anomaly detection in dynamic scenes with moving cameras","created":"2023-08-14","cited_by_count":10,"area":null},{"id":"2401.16424","title":"Computer Vision for Primate Behavior Analysis in the Wild","created":"2024-01-29","cited_by_count":10,"area":null},{"id":"2411.08466","title":"Weakly Supervised Temporal Action Localization via Dual-Prior Collaborative Learning Guided by Multimodal Large Language Models","created":"2024-11-13","cited_by_count":10,"area":"mllm"},{"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":"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":"2501.11124","title":"Rethinking Pseudo-Label Guided Learning for Weakly Supervised Temporal Action Localization from the Perspective of Noise Correction","created":"2025-01-19","cited_by_count":8,"area":"distill"},{"id":"2108.05607","title":"Deep Motion Prior for Weakly-Supervised Temporal Action Localization","created":"2021-08-12","cited_by_count":7,"area":null},{"id":"2205.09956","title":"Structured Attention Composition for Temporal Action Localization","created":"2022-05-20","cited_by_count":7,"area":null},{"id":"2208.03775","title":"Video-based Human Action Recognition using Deep Learning: A Review","created":"2022-08-07","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":"2203.08942","title":"ABN: Agent-Aware Boundary Networks for Temporal Action Proposal Generation","created":"2022-03-16","cited_by_count":6,"area":null},{"id":"2203.16244","title":"CycDA: Unsupervised Cycle Domain Adaptation from Image to Video","created":"2022-03-30","cited_by_count":6,"area":null},{"id":"2212.10596","title":"Open-Vocabulary Temporal Action Detection with Off-the-Shelf Image-Text Features","created":"2022-12-20","cited_by_count":6,"area":null},{"id":"2407.07024","title":"Exploring Scalability of Self-Training for Open-Vocabulary Temporal Action Localization","created":"2024-07-09","cited_by_count":6,"area":"mllm"},{"id":"2504.14860","title":"Bridge the Gap: From Weak to Full Supervision for Temporal Action Localization with PseudoFormer","created":"2025-04-21","cited_by_count":6,"area":null},{"id":"2203.01542","title":"SegTAD: Precise Temporal Action Detection via Semantic Segmentation","created":"2022-03-03","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":"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":"2308.09322","title":"Audio-Visual Glance Network for Efficient Video Recognition","created":"2023-08-18","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":"2404.03179","title":"UniAV: Unified Audio-Visual Perception for Multi-Task Video Event Localization","created":"2024-04-04","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":"2104.11637","title":"Online recognition of unsegmented actions with hierarchical SOM architecture","created":"2021-04-23","cited_by_count":3,"area":null},{"id":"2201.00434","title":"TVNet: Temporal Voting Network for Action Localization","created":"2022-01-02","cited_by_count":3,"area":null},{"id":"2211.14905","title":"Multi-Modal Few-Shot Temporal Action Detection","created":"2022-11-27","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":"2403.18915","title":"PLOT-TAL: Prompt Learning with Optimal Transport for Few-Shot Temporal Action Localization","created":"2024-03-27","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":"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":"2205.00400","title":"Convex Combination Consistency between Neighbors for Weakly-supervised Action Localization","created":"2022-05-01","cited_by_count":2,"area":null},{"id":"2206.10095","title":"Pyramid Region-based Slot Attention Network for Temporal Action Proposal Generation","created":"2022-06-21","cited_by_count":2,"area":null}],"next_cursor":"100"}