{"total":152,"rows":[{"id":"2203.01577","title":"HOI4D: A 4D Egocentric Dataset for Category-Level Human-Object Interaction","created":"2022-03-03","cited_by_count":327,"area":null},{"id":"2305.13292","title":"VideoLLM: Modeling Video Sequence with Large Language Models","created":"2023-05-22","cited_by_count":116,"area":null},{"id":"2210.10352","title":"Temporal Action Segmentation: An Analysis of Modern Techniques","created":"2022-10-19","cited_by_count":85,"area":null},{"id":"2303.17959","title":"Diffusion Action Segmentation","created":"2023-03-31","cited_by_count":74,"area":null},{"id":"2205.14022","title":"Future Transformer for Long-term Action Anticipation","created":"2022-05-27","cited_by_count":58,"area":null},{"id":"2407.04689","title":"RAM: Retrieval-Based Affordance Transfer for Generalizable Zero-Shot Robotic Manipulation","created":"2024-07-05","cited_by_count":58,"area":null},{"id":"2401.00496","title":"SAR-RARP50: Segmentation of surgical instrumentation and Action Recognition on Robot-Assisted Radical Prostatectomy Challenge","created":"2023-12-31","cited_by_count":56,"area":null},{"id":"2209.00638","title":"Unified Fully and Timestamp Supervised Temporal Action Segmentation via Sequence to Sequence Translation","created":"2022-09-01","cited_by_count":55,"area":null},{"id":"2203.14104","title":"Bridge-Prompt: Towards Ordinal Action Understanding in Instructional Videos","created":"2022-03-26","cited_by_count":50,"area":null},{"id":"2210.07503","title":"STAR-Transformer: A Spatio-temporal Cross Attention Transformer for Human Action Recognition","created":"2022-10-14","cited_by_count":43,"area":null},{"id":"2207.10213","title":"Spotting Temporally Precise, Fine-Grained Events in Video","created":"2022-07-20","cited_by_count":40,"area":null},{"id":"2404.01518","title":"Temporally Consistent Unbalanced Optimal Transport for Unsupervised Action Segmentation","created":"2024-04-01","cited_by_count":38,"area":null},{"id":"2308.11358","title":"How Much Temporal Long-Term Context is Needed for Action Segmentation?","created":"2023-08-22","cited_by_count":36,"area":null},{"id":"2207.09270","title":"Action Quality Assessment with Temporal Parsing Transformer","created":"2022-07-19","cited_by_count":31,"area":null},{"id":"2404.05029","title":"LOGO: A Long-Form Video Dataset for Group Action Quality Assessment","created":"2024-04-07","cited_by_count":31,"area":null},{"id":"2306.03802","title":"Learning to Ground Instructional Articles in Videos through Narrations","created":"2023-06-06","cited_by_count":28,"area":null},{"id":"2209.05700","title":"Vision Transformers for Action Recognition: A Survey","created":"2022-09-13","cited_by_count":25,"area":null},{"id":"2501.03674","title":"Action Quality Assessment via Hierarchical Pose-guided Multi-stage Contrastive Regression","created":"2025-01-07","cited_by_count":21,"area":null},{"id":"2503.00986","title":"Modeling Fine-Grained Hand-Object Dynamics for Egocentric Video Representation Learning","created":"2025-03-02","cited_by_count":20,"area":null},{"id":"2203.07976","title":"On the Pitfalls of Batch Normalization for End-to-End Video Learning: A Study on Surgical Workflow Analysis","created":"2022-03-15","cited_by_count":19,"area":null},{"id":"2412.17640","title":"Hierarchical Vector Quantization for Unsupervised Action Segmentation","created":"2024-12-23","cited_by_count":19,"area":null},{"id":"2305.19478","title":"Permutation-Aware Action Segmentation via Unsupervised Frame-to-Segment Alignment","created":"2023-05-31","cited_by_count":17,"area":null},{"id":"2112.06447","title":"SVIP: Sequence VerIfication for Procedures in Videos","created":"2021-12-13","cited_by_count":16,"area":null},{"id":"2205.09445","title":"Cross-Enhancement Transformer for Action Segmentation","created":"2022-05-19","cited_by_count":14,"area":null},{"id":"2305.13961","title":"Metrics Matter in Surgical Phase Recognition","created":"2023-05-23","cited_by_count":14,"area":null},{"id":"2403.19225","title":"Efficient and Effective Weakly-Supervised Action Segmentation via Action-Transition-Aware Boundary Alignment","created":"2024-03-28","cited_by_count":13,"area":null},{"id":"2503.18359","title":"Context-Enhanced Memory-Refined Transformer for Online Action Detection","created":"2025-03-24","cited_by_count":13,"area":null},{"id":"2402.00293","title":"FineBio: A Fine-Grained Video Dataset of Biological Experiments with Hierarchical Annotation","created":"2024-02-01","cited_by_count":12,"area":null},{"id":"2503.22405","title":"Modeling Multiple Normal Action Representations for Error Detection in Procedural Tasks","created":"2025-03-28","cited_by_count":12,"area":null},{"id":"2307.03353","title":"A Survey of Deep Learning in Sports Applications: Perception, Comprehension, and Decision","created":"2023-07-07","cited_by_count":11,"area":null},{"id":"2205.13425","title":"Do we really need temporal convolutions in action segmentation?","created":"2022-05-26","cited_by_count":10,"area":null},{"id":"2310.09114","title":"Timestamp-supervised Wearable-based Activity Segmentation and Recognition with Contrastive Learning and Order-Preserving Optimal Transport","created":"2023-10-13","cited_by_count":10,"area":null},{"id":"2405.15995","title":"Efficient Temporal Action Segmentation via Boundary-aware Query Voting","created":"2024-05-25","cited_by_count":10,"area":null},{"id":"2209.05653","title":"Semantic2Graph: Graph-based Multi-modal Feature Fusion for Action Segmentation in Videos","created":"2022-09-13","cited_by_count":9,"area":null},{"id":"2504.00072","title":"Chapter-Llama: Efficient Chaptering in Hour-Long Videos with LLMs","created":"2025-03-31","cited_by_count":9,"area":null},{"id":"2312.04266","title":"Activity Grammars for Temporal Action Segmentation","created":"2023-12-07","cited_by_count":8,"area":null},{"id":"2312.05830","title":"A Decoupled Spatio-Temporal Framework for Skeleton-based Action Segmentation","created":"2023-12-10","cited_by_count":8,"area":null},{"id":"2404.09951","title":"Unifying Global and Local Scene Entities Modelling for Precise Action Spotting","created":"2024-04-15","cited_by_count":8,"area":null},{"id":"2507.16559","title":"Comparative validation of surgical phase recognition, instrument keypoint estimation, and instrument instance segmentation in endoscopy: Results of the PhaKIR 2024 challenge","created":"2025-07-22","cited_by_count":8,"area":null},{"id":"2304.03631","title":"Therbligs in Action: Video Understanding through Motion Primitives","created":"2023-04-06","cited_by_count":7,"area":null},{"id":"2402.15952","title":"ViSTec: Video Modeling for Sports Technique Recognition and Tactical Analysis","created":"2024-02-25","cited_by_count":7,"area":null},{"id":"2408.16638","title":"3D Pose-Based Temporal Action Segmentation for Figure Skating: A Fine-Grained and Jump Procedure-Aware Annotation Approach","created":"2024-08-29","cited_by_count":7,"area":null},{"id":"2410.01304","title":"Deep learning for action spotting in association football videos","created":"2024-10-02","cited_by_count":7,"area":null},{"id":"2411.01122","title":"OnlineTAS: An Online Baseline for Temporal Action Segmentation","created":"2024-11-02","cited_by_count":7,"area":null},{"id":"2504.08222","title":"F$^3$Set: Towards Analyzing Fast, Frequent, and Fine-grained Events from Videos","created":"2025-04-11","cited_by_count":7,"area":null},{"id":"2210.06501","title":"Robust Action Segmentation from Timestamp Supervision","created":"2022-10-12","cited_by_count":6,"area":null},{"id":"2307.09997","title":"TUNeS: A Temporal U-Net with Self-Attention for Video-based Surgical Phase Recognition","created":"2023-07-19","cited_by_count":6,"area":null},{"id":"2401.09057","title":"CrossVideo: Self-supervised Cross-modal Contrastive Learning for Point Cloud Video Understanding","created":"2024-01-17","cited_by_count":6,"area":null},{"id":"2407.11954","title":"Gated Temporal Diffusion for Stochastic Long-Term Dense Anticipation","created":"2024-07-16","cited_by_count":6,"area":null},{"id":"2503.00147","title":"Precise Event Spotting in Sports Videos: Solving Long-Range Dependency and Class Imbalance","created":"2025-02-28","cited_by_count":6,"area":null},{"id":"2503.21055","title":"What Changed and What Could Have Changed? State-Change Counterfactuals for Procedure-Aware Video Representation Learning","created":"2025-03-27","cited_by_count":6,"area":null},{"id":"2507.03539","title":"CLOT: Closed Loop Optimal Transport for Unsupervised Action Segmentation","created":"2025-07-04","cited_by_count":6,"area":null},{"id":"2508.04513","title":"Skeleton Motion Words for Unsupervised Skeleton-Based Temporal Action Segmentation","created":"2025-08-06","cited_by_count":6,"area":null},{"id":"2209.14647","title":"Bounded Future MS-TCN++ for surgical gesture recognition","created":"2022-09-29","cited_by_count":5,"area":null},{"id":"2306.08859","title":"SF-TMN: SlowFast Temporal Modeling Network for Surgical Phase Recognition","created":"2023-06-15","cited_by_count":5,"area":null},{"id":"2403.06102","title":"Coherent Temporal Synthesis for Incremental Action Segmentation","created":"2024-03-10","cited_by_count":5,"area":null},{"id":"2201.05675","title":"Transformers in Action: Weakly Supervised Action Segmentation","created":"2022-01-14","cited_by_count":4,"area":null},{"id":"2206.12672","title":"SKTR: Trace Recovery from Stochastically Known Logs","created":"2022-06-25","cited_by_count":4,"area":null},{"id":"2208.14209","title":"A Circular Window-based Cascade Transformer for Online Action Detection","created":"2022-08-30","cited_by_count":4,"area":null},{"id":"2212.11694","title":"Timestamp-Supervised Action Segmentation from the Perspective of Clustering","created":"2022-12-22","cited_by_count":4,"area":null},{"id":"2308.16552","title":"Prompt-enhanced Hierarchical Transformer Elevating Cardiopulmonary Resuscitation Instruction via Temporal Action Segmentation","created":"2023-08-31","cited_by_count":4,"area":null},{"id":"2409.05662","title":"Real-Time Human Action Recognition on Embedded Platforms","created":"2024-09-09","cited_by_count":4,"area":null},{"id":"2503.11392","title":"Watch and Learn: Leveraging Expert Knowledge and Language for Surgical Video Understanding","created":"2025-03-14","cited_by_count":4,"area":null},{"id":"2503.14112","title":"Condensing Action Segmentation Datasets via Generative Network Inversion","created":"2025-03-18","cited_by_count":4,"area":null},{"id":"2302.13074","title":"Temporal Segment Transformer for Action Segmentation","created":"2023-02-25","cited_by_count":3,"area":null},{"id":"2305.11365","title":"Enhancing Transformer Backbone for Egocentric Video Action Segmentation","created":"2023-05-19","cited_by_count":3,"area":null},{"id":"2306.06960","title":"Semantic Parsing of Colonoscopy Videos with Multi-Label Temporal Networks","created":"2023-06-12","cited_by_count":3,"area":null},{"id":"2408.09919","title":"Long-Tail Temporal Action Segmentation with Group-wise Temporal Logit Adjustment","created":"2024-08-19","cited_by_count":3,"area":null},{"id":"2412.12829","title":"2by2: Weakly-Supervised Learning for Global Action Segmentation","created":"2024-12-17","cited_by_count":3,"area":null},{"id":"2510.01362","title":"EvoStruggle: A Dataset Capturing the Evolution of Struggle across Activities and Skill Levels","created":"2025-10-01","cited_by_count":3,"area":null},{"id":"2510.16371","title":"Cataract-LMM Large-Scale Multi-Source Multi-Task Benchmark for Deep Learning in Surgical Video Analysis","created":"2025-10-18","cited_by_count":3,"area":null},{"id":"2604.26227","title":"HOI-aware Adaptive Network for Weakly-supervised Action Segmentation","created":"2026-04-29","cited_by_count":3,"area":null},{"id":"2209.12221","title":"Hand Hygiene Assessment via Joint Step Segmentation and Key Action Scorer","created":"2022-09-25","cited_by_count":2,"area":null},{"id":"2303.05166","title":"TAEC: Unsupervised Action Segmentation with Temporal-Aware Embedding and Clustering","created":"2023-03-09","cited_by_count":2,"area":null},{"id":"2304.02110","title":"DIR-AS: Decoupling Individual Identification and Temporal Reasoning for Action Segmentation","created":"2023-04-04","cited_by_count":2,"area":null},{"id":"2401.08381","title":"Robotic Imitation of Human Actions","created":"2024-01-16","cited_by_count":2,"area":null},{"id":"2401.11644","title":"Friends Across Time: Multi-Scale Action Segmentation Transformer for Surgical Phase Recognition","created":"2024-01-22","cited_by_count":2,"area":null},{"id":"2405.02571","title":"ViTALS: Vision Transformer for Action Localization in Surgical Nephrectomy","created":"2024-05-04","cited_by_count":2,"area":null},{"id":"2408.00041","title":"Con4m: Context-aware Consistency Learning Framework for Segmented Time Series Classification","created":"2024-07-31","cited_by_count":2,"area":null},{"id":"2410.06353","title":"Language-Assisted Human Part Motion Learning for Skeleton-Based Temporal Action Segmentation","created":"2024-10-08","cited_by_count":2,"area":null},{"id":"2412.04039","title":"Benchmarking and Enhancing Surgical Phase Recognition Models for Robotic-Assisted Esophagectomy","created":"2024-12-05","cited_by_count":2,"area":null},{"id":"2503.15126","title":"Text-Derived Relational Graph-Enhanced Network for Skeleton-Based Action Segmentation","created":"2025-03-19","cited_by_count":2,"area":null},{"id":"2503.18553","title":"ATARS: An Aerial Traffic Atomic Activity Recognition and Temporal Segmentation Dataset","created":"2025-03-24","cited_by_count":2,"area":null},{"id":"2603.09741","title":"ENIGMA-360: An Ego-Exo Dataset for Human Behavior Understanding in Industrial Scenarios","created":"2026-03-10","cited_by_count":2,"area":null},{"id":"2604.12343","title":"Detecting Precise Hand Touch Moments in Egocentric Video","created":"2026-04-14","cited_by_count":2,"area":null},{"id":"2209.13808","title":"Streaming Video Temporal Action Segmentation In Real Time","created":"2022-09-28","cited_by_count":1,"area":null},{"id":"2309.15683","title":"End-to-End Streaming Video Temporal Action Segmentation with Reinforce Learning","created":"2023-09-27","cited_by_count":1,"area":null},{"id":"2311.12401","title":"CASR: Refining Action Segmentation via Marginalizing Frame-levle Causal Relationships","created":"2023-11-21","cited_by_count":1,"area":null},{"id":"2311.17428","title":"SigFormer: Sparse Signal-Guided Transformer for Multi-Modal Human Action Segmentation","created":"2023-11-29","cited_by_count":1,"area":null},{"id":"2312.12347","title":"SMC-NCA: Semantic-guided Multi-level Contrast for Semi-supervised Temporal Action Segmentation","created":"2023-12-19","cited_by_count":1,"area":null},{"id":"2406.08814","title":"Skim then Focus: Integrating Contextual and Fine-grained Views for Repetitive Action Counting","created":"2024-06-13","cited_by_count":1,"area":null},{"id":"2408.11318","title":"TWLV-I: Analysis and Insights from Holistic Evaluation on Video Foundation Models","created":"2024-08-21","cited_by_count":1,"area":null},{"id":"2409.18478","title":"Temporal2Seq: A Unified Framework for Temporal Video Understanding Tasks","created":"2024-09-27","cited_by_count":1,"area":null},{"id":"2502.03430","title":"A Temporal Convolutional Network-Based Approach and a Benchmark Dataset for Colonoscopy Video Temporal Segmentation","created":"2025-02-05","cited_by_count":1,"area":null},{"id":"2502.10713","title":"Improving action segmentation via explicit similarity measurement","created":"2025-02-15","cited_by_count":1,"area":null},{"id":"2503.06316","title":"End-to-End Action Segmentation Transformer","created":"2025-03-08","cited_by_count":1,"area":null},{"id":"2504.06580","title":"Exploring Ordinal Bias in Action Recognition for Instructional Videos","created":"2025-04-09","cited_by_count":1,"area":null},{"id":"2507.00756","title":"Towards Open-World Human Action Segmentation Using Graph Convolutional Networks","created":"2025-07-01","cited_by_count":1,"area":null},{"id":"2507.09294","title":"Geo-RepNet: Geometry-Aware Representation Learning for Surgical Phase Recognition in Endoscopic Submucosal Dissection","created":"2025-07-12","cited_by_count":1,"area":null},{"id":"2508.05529","title":"Looking into the Unknown: Exploring Action Discovery for Segmentation of Known and Unknown Actions","created":"2025-08-07","cited_by_count":1,"area":null}],"next_cursor":"100"}