{"total":116,"rows":[{"id":"2109.14084","title":"VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding","created":"2021-09-28","cited_by_count":602,"area":null},{"id":"2311.18259","title":"Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives","created":"2023-11-30","cited_by_count":490,"area":null},{"id":"2106.02636","title":"MERLOT: Multimodal Neural Script Knowledge Models","created":"2021-06-04","cited_by_count":311,"area":null},{"id":"2203.14712","title":"Assembly101: A Large-Scale Multi-View Video Dataset for Understanding Procedural Activities","created":"2022-03-28","cited_by_count":287,"area":null},{"id":"2309.17024","title":"HoloAssist: an Egocentric Human Interaction Dataset for Interactive AI Assistants in the Real World","created":"2023-09-29","cited_by_count":166,"area":null},{"id":"2210.03929","title":"EgoTaskQA: Understanding Human Tasks in Egocentric Videos","created":"2022-10-08","cited_by_count":115,"area":null},{"id":"2103.16559","title":"Broaden Your Views for Self-Supervised Video Learning","created":"2021-03-30","cited_by_count":108,"area":null},{"id":"2303.14717","title":"CelebV-Text: A Large-Scale Facial Text-Video Dataset","created":"2023-03-26","cited_by_count":104,"area":null},{"id":"2105.09996","title":"VLM: Task-agnostic Video-Language Model Pre-training for Video Understanding","created":"2021-05-20","cited_by_count":102,"area":null},{"id":"2108.09980","title":"TACo: Token-aware Cascade Contrastive Learning for Video-Text Alignment","created":"2021-08-23","cited_by_count":102,"area":"mllm"},{"id":"2210.10352","title":"Temporal Action Segmentation: An Analysis of Modern Techniques","created":"2022-10-19","cited_by_count":85,"area":null},{"id":"2207.10883","title":"My View is the Best View: Procedure Learning from Egocentric Videos","created":"2022-07-22","cited_by_count":81,"area":null},{"id":"2304.06708","title":"Verbs in Action: Improving verb understanding in video-language models","created":"2023-04-13","cited_by_count":76,"area":null},{"id":"2103.11264","title":"Temporally-Weighted Hierarchical Clustering for Unsupervised Action Segmentation","created":"2021-03-20","cited_by_count":58,"area":null},{"id":"2105.04489","title":"Spoken Moments: Learning Joint Audio-Visual Representations from Video Descriptions","created":"2021-05-10","cited_by_count":53,"area":null},{"id":"2110.01770","title":"Procedure Planning in Instructional Videos via Contextual Modeling and Model-based Policy Learning","created":"2021-10-05","cited_by_count":53,"area":null},{"id":"2205.02300","title":"P3IV: Probabilistic Procedure Planning from Instructional Videos with Weak Supervision","created":"2022-05-04","cited_by_count":52,"area":null},{"id":"2105.13353","title":"Unsupervised Action Segmentation by Joint Representation Learning and Online Clustering","created":"2021-05-27","cited_by_count":49,"area":null},{"id":"2303.18230","title":"Procedure-Aware Pretraining for Instructional Video Understanding","created":"2023-03-31","cited_by_count":48,"area":null},{"id":"2303.17839","title":"Learning Procedure-aware Video Representation from Instructional Videos and Their Narrations","created":"2023-03-31","cited_by_count":46,"area":null},{"id":"2207.10362","title":"LocVTP: Video-Text Pre-training for Temporal Localization","created":"2022-07-21","cited_by_count":44,"area":null},{"id":"2103.08849","title":"Multilingual Multimodal Pre-training for Zero-Shot Cross-Lingual Transfer of Vision-Language Models","created":"2021-03-16","cited_by_count":41,"area":"mllm"},{"id":"2203.11637","title":"Look for the Change: Learning Object States and State-Modifying Actions from Untrimmed Web Videos","created":"2022-03-22","cited_by_count":39,"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":"2303.14676","title":"PDPP: Projected Diffusion for Procedure Planning in Instructional Videos","created":"2023-03-26","cited_by_count":36,"area":null},{"id":"2208.06773","title":"TL;DW? Summarizing Instructional Videos with Task Relevance & Cross-Modal Saliency","created":"2022-08-14","cited_by_count":35,"area":null},{"id":"2307.08763","title":"Video-Mined Task Graphs for Keystep Recognition in Instructional Videos","created":"2023-07-17","cited_by_count":35,"area":null},{"id":"2104.02116","title":"Action Shuffle Alternating Learning for Unsupervised Action Segmentation","created":"2021-04-05","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":"2306.03802","title":"Learning to Ground Instructional Articles in Videos through Narrations","created":"2023-06-06","cited_by_count":28,"area":null},{"id":"2105.00067","title":"Unsupervised Discriminative Embedding for Sub-Action Learning in Complex Activities","created":"2021-04-30","cited_by_count":26,"area":null},{"id":"2203.16784","title":"Video-Text Representation Learning via Differentiable Weak Temporal Alignment","created":"2022-03-31","cited_by_count":24,"area":null},{"id":"2403.01599","title":"SCHEMA: State CHangEs MAtter for Procedure Planning in Instructional Videos","created":"2024-03-03","cited_by_count":24,"area":null},{"id":"2203.07264","title":"Show Me More Details: Discovering Hierarchies of Procedures from Semi-structured Web Data","created":"2022-03-14","cited_by_count":22,"area":null},{"id":"2308.08885","title":"Event-Guided Procedure Planning from Instructional Videos with Text Supervision","created":"2023-08-17","cited_by_count":21,"area":null},{"id":"2412.17640","title":"Hierarchical Vector Quantization for Unsupervised Action Segmentation","created":"2024-12-23","cited_by_count":19,"area":null},{"id":"2206.15031","title":"Timestamp-Supervised Action Segmentation with Graph Convolutional Networks","created":"2022-06-30","cited_by_count":18,"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":"2108.06706","title":"Temporal Action Segmentation with High-level Complex Activity Labels","created":"2021-08-15","cited_by_count":16,"area":null},{"id":"2112.06447","title":"SVIP: Sequence VerIfication for Procedures in Videos","created":"2021-12-13","cited_by_count":16,"area":null},{"id":"2203.16071","title":"Learning Program Representations for Food Images and Cooking Recipes","created":"2022-03-30","cited_by_count":16,"area":null},{"id":"2105.14158","title":"SSCAP: Self-supervised Co-occurrence Action Parsing for Unsupervised Temporal Action Segmentation","created":"2021-05-29","cited_by_count":15,"area":null},{"id":"2212.13738","title":"TempCLR: Temporal Alignment Representation with Contrastive Learning","created":"2022-12-28","cited_by_count":15,"area":null},{"id":"2403.02782","title":"Why Not Use Your Textbook? Knowledge-Enhanced Procedure Planning of Instructional Videos","created":"2024-03-05","cited_by_count":15,"area":null},{"id":"2101.02337","title":"Learning Temporal Dynamics from Cycles in Narrated Video","created":"2021-01-07","cited_by_count":13,"area":null},{"id":"2301.00794","title":"STEPs: Self-Supervised Key Step Extraction and Localization from Unlabeled Procedural Videos","created":"2023-01-02","cited_by_count":13,"area":null},{"id":"2311.03550","title":"United We Stand, Divided We Fall: UnityGraph for Unsupervised Procedure Learning from Videos","created":"2023-11-06","cited_by_count":13,"area":null},{"id":"2104.04182","title":"FIBER: Fill-in-the-Blanks as a Challenging Video Understanding Evaluation Framework","created":"2021-04-09","cited_by_count":12,"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":"2411.11409","title":"IKEA Manuals at Work: 4D Grounding of Assembly Instructions on Internet Videos","created":"2024-11-18","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":"2309.06276","title":"OTAS: Unsupervised Boundary Detection for Object-Centric Temporal Action Segmentation","created":"2023-09-12","cited_by_count":11,"area":null},{"id":"2311.16444","title":"Exo2EgoDVC: Dense Video Captioning of Egocentric Procedural Activities Using Web Instructional Videos","created":"2023-11-28","cited_by_count":11,"area":null},{"id":"2503.16832","title":"Joint Self-Supervised Video Alignment and Action Segmentation","created":"2025-03-21","cited_by_count":11,"area":null},{"id":"2106.03158","title":"Transferring Knowledge from Text to Video: Zero-Shot Anticipation for Procedural Actions","created":"2021-06-06","cited_by_count":10,"area":null},{"id":"2304.06403","title":"Leveraging triplet loss for unsupervised action segmentation","created":"2023-04-13","cited_by_count":10,"area":null},{"id":"2111.01591","title":"Estimating 3D Motion and Forces of Human-Object Interactions from Internet Videos","created":"2021-11-02","cited_by_count":9,"area":null},{"id":"2410.14045","title":"Human Action Anticipation: A Survey","created":"2024-10-17","cited_by_count":9,"area":null},{"id":"2403.08591","title":"ActionDiffusion: An Action-aware Diffusion Model for Procedure Planning in Instructional Videos","created":"2024-03-13","cited_by_count":8,"area":"diffusion"},{"id":"2109.15170","title":"CoSeg: Cognitively Inspired Unsupervised Generic Event Segmentation","created":"2021-09-30","cited_by_count":7,"area":null},{"id":"2309.07409","title":"Masked Diffusion with Task-awareness for Procedure Planning in Instructional Videos","created":"2023-09-14","cited_by_count":7,"area":"diffusion"},{"id":"2405.15813","title":"From CNNs to Transformers in Multimodal Human Action Recognition: A Survey","created":"2024-05-22","cited_by_count":7,"area":null},{"id":"2410.03478","title":"VEDIT: Latent Prediction Architecture For Procedural Video Representation Learning","created":"2024-10-04","cited_by_count":7,"area":null},{"id":"2104.00285","title":"CUPID: Adaptive Curation of Pre-training Data for Video-and-Language Representation Learning","created":"2021-04-01","cited_by_count":6,"area":null},{"id":"2302.09173","title":"Unsupervised Task Graph Generation from Instructional Video Transcripts","created":"2023-02-17","cited_by_count":6,"area":null},{"id":"2303.14829","title":"SEM-POS: Grammatically and Semantically Correct Video Captioning","created":"2023-03-26","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":"2212.11471","title":"Multi-queue Momentum Contrast for Microvideo-Product Retrieval","created":"2022-12-22","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":"2507.03393","title":"Masked Temporal Interpolation Diffusion for Procedure Planning in Instructional Videos","created":"2025-07-04","cited_by_count":5,"area":null},{"id":"2511.13261","title":"Building Egocentric Procedural AI Assistant: Methods, Benchmarks, and Challenges","created":"2025-11-17","cited_by_count":5,"area":"mllm"},{"id":"2102.02789","title":"Disambiguation of weak supervision with exponential convergence rates","created":"2021-02-04","cited_by_count":4,"area":null},{"id":"2106.03738","title":"Unsupervised Action Segmentation for Instructional Videos","created":"2021-06-07","cited_by_count":4,"area":null},{"id":"2207.05182","title":"Fine-grained Activities of People Worldwide","created":"2022-07-11","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":"2405.01090","title":"Learning Multiple Object States from Actions via Large Language Models","created":"2024-05-02","cited_by_count":4,"area":null},{"id":"2507.15540","title":"Procedure Learning via Regularized Gromov-Wasserstein Optimal Transport","created":"2025-07-21","cited_by_count":4,"area":null},{"id":"2603.04265","title":"ViterbiPlanNet: Injecting Procedural Knowledge via Differentiable Viterbi for Planning in Instructional Videos","created":"2026-03-04","cited_by_count":4,"area":null},{"id":"2109.07951","title":"Overview of Tencent Multi-modal Ads Video Understanding Challenge","created":"2021-09-16","cited_by_count":3,"area":null},{"id":"2210.16644","title":"Unsupervised Audio-Visual Lecture Segmentation","created":"2022-10-29","cited_by_count":3,"area":null},{"id":"2407.05119","title":"Open-Event Procedure Planning in Instructional Videos","created":"2024-07-06","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":"2607.29401","title":"OSEF: One-Step Evidence Fusion for Cross-Video Scene Procedure Planning","created":"2026-07-31","cited_by_count":3,"area":null},{"id":"2106.14733","title":"Unsupervised Discovery of Actions in Instructional Videos","created":"2021-06-28","cited_by_count":2,"area":null},{"id":"2203.15778","title":"Text-Driven Video Acceleration: A Weakly-Supervised Reinforcement Learning Method","created":"2022-03-29","cited_by_count":2,"area":null},{"id":"2211.01824","title":"Human in the loop approaches in multi-modal conversational task guidance system development","created":"2022-11-03","cited_by_count":2,"area":null},{"id":"2212.04700","title":"Tencent AVS: A Holistic Ads Video Dataset for Multi-modal Scene Segmentation","created":"2022-12-09","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":"2503.06637","title":"CLAD: Constrained Latent Action Diffusion for Vision-Language Procedure Planning","created":"2025-03-09","cited_by_count":2,"area":"diffusion"},{"id":"2603.08648","title":"CAST: Modeling Visual State Transitions for Consistent Video Retrieval","created":"2026-03-09","cited_by_count":2,"area":null},{"id":"2112.12409","title":"InstaIndoor and Multi-modal Deep Learning for Indoor Scene Recognition","created":"2021-12-23","cited_by_count":1,"area":null},{"id":"2202.08138","title":"When Did It Happen? Duration-informed Temporal Localization of Narrated Actions in Vlogs","created":"2022-02-16","cited_by_count":1,"area":null},{"id":"2208.06662","title":"Self-Contained Entity Discovery from Captioned Videos","created":"2022-08-13","cited_by_count":1,"area":null},{"id":"2506.21249","title":"Temporal Rate Reduction Clustering for Human Motion Segmentation","created":"2025-06-26","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},{"id":"2508.11192","title":"Generating Dialogues from Egocentric Instructional Videos for Task Assistance: Dataset, Method and Benchmark","created":"2025-08-15","cited_by_count":1,"area":null},{"id":"2509.24382","title":"REMAP: Regularized Matching and Partial Alignment of Video Embeddings","created":"2025-09-29","cited_by_count":1,"area":null},{"id":"2602.24275","title":"Hierarchical Action Learning for Weakly-Supervised Action Segmentation","created":"2026-02-27","cited_by_count":1,"area":null},{"id":"2603.09743","title":"LAP: A Language-Aware Planning Model For Procedure Planning In Instructional Videos","created":"2026-03-10","cited_by_count":1,"area":null}],"next_cursor":"100"}