{"list":"other","total":73,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"1812.03982","title":"SlowFast Networks for Video Recognition","created":"2018-12-10","cited_by_count":1867},{"id":"2102.05095","title":"Is Space-Time Attention All You Need for Video Understanding?","created":"2021-02-09","cited_by_count":1620},{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"id":"1902.09212","title":"Deep High-Resolution Representation Learning for Human Pose Estimation","created":"2019-02-25","cited_by_count":1339},{"id":"2004.09297","title":"MPNet: Masked and Permuted Pre-training for Language Understanding","created":"2020-04-20","cited_by_count":981},{"id":"1906.03327","title":"HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips","created":"2019-06-07","cited_by_count":950},{"id":"1603.06937","title":"Stacked Hourglass Networks for Human Pose Estimation","created":"2016-03-22","cited_by_count":915},{"id":"1703.09788","title":"Towards Automatic Learning of Procedures from Web Instructional Videos","created":"2017-03-28","cited_by_count":619},{"id":"2109.14084","title":"VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding","created":"2021-09-28","cited_by_count":602},{"id":"2112.01526","title":"MViTv2: Improved Multiscale Vision Transformers for Classification and Detection","created":"2021-12-02","cited_by_count":519},{"id":"1912.06430","title":"End-to-End Learning of Visual Representations from Uncurated Instructional Videos","created":"2019-12-13","cited_by_count":507},{"id":"2311.18259","title":"Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives","created":"2023-11-30","cited_by_count":490},{"id":"2204.12484","title":"ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation","created":"2022-04-26","cited_by_count":456},{"id":"2005.00200","title":"HERO: Hierarchical Encoder for Video+Language Omni-representation Pre-training","created":"2020-05-01","cited_by_count":362},{"id":"1808.01340","title":"A Short Note about Kinetics-600","created":"2018-08-03","cited_by_count":333},{"id":"1609.08675","title":"YouTube-8M: A Large-Scale Video Classification Benchmark","created":"2016-09-27","cited_by_count":324},{"id":"1903.02874","title":"COIN: A Large-scale Dataset for Comprehensive Instructional Video Analysis","created":"2019-03-07","cited_by_count":318},{"id":"1312.4659","title":"DeepPose: Human Pose Estimation via Deep Neural Networks","created":"2013-12-17","cited_by_count":305},{"id":"2004.06704","title":"FineGym: A Hierarchical Video Dataset for Fine-grained Action Understanding","created":"2020-04-14","cited_by_count":234},{"id":"2206.01670","title":"Egocentric Video-Language Pretraining","created":"2022-06-03","cited_by_count":232},{"id":"2201.08377","title":"Omnivore: A Single Model for Many Visual Modalities","created":"2022-01-20","cited_by_count":215},{"id":"1604.06182","title":"The THUMOS Challenge on Action Recognition for Videos \"in the Wild\"","created":"2016-04-21","cited_by_count":213},{"id":"2201.09450","title":"UniFormer: Unifying Convolution and Self-attention for Visual Recognition","created":"2022-01-24","cited_by_count":206},{"id":"2312.07531","title":"WHAM: Reconstructing World-grounded Humans with Accurate 3D Motion","created":"2023-12-12","cited_by_count":206},{"id":"2106.02036","title":"Anticipative Video Transformer","created":"2021-06-03","cited_by_count":200},{"id":"1704.07333","title":"Detecting and Recognizing Human-Object Interactions","created":"2017-04-24","cited_by_count":199},{"id":"1903.08225","title":"Cross-task weakly supervised learning from instructional videos","created":"2019-03-19","cited_by_count":199},{"id":"2201.08383","title":"MeMViT: Memory-Augmented Multiscale Vision Transformer for Efficient Long-Term Video Recognition","created":"2022-01-20","cited_by_count":189},{"id":"2104.13682","title":"HOTR: End-to-End Human-Object Interaction Detection with Transformers","created":"2021-04-28","cited_by_count":183},{"id":"1804.04527","title":"SoccerNet: A Scalable Dataset for Action Spotting in Soccer Videos","created":"2018-04-12","cited_by_count":150},{"id":"2103.05399","title":"QPIC: Query-Based Pairwise Human-Object Interaction Detection with Image-Wide Contextual Information","created":"2021-03-09","cited_by_count":147},{"id":"2307.05463","title":"EgoVLPv2: Egocentric Video-Language Pre-training with Fusion in the Backbone","created":"2023-07-11","cited_by_count":130},{"id":"2005.02190","title":"Rolling-Unrolling LSTMs for Action Anticipation from First-Person Video","created":"2020-05-04","cited_by_count":120},{"id":"2003.14023","title":"Learning Human-Object Interaction Detection using Interaction Points","created":"2020-03-31","cited_by_count":108},{"id":"1804.00892","title":"When will you do what? - Anticipating Temporal Occurrences of Activities","created":"2018-04-03","cited_by_count":107},{"id":"2204.03646","title":"FineDiving: A Fine-grained Dataset for Procedure-aware Action Quality Assessment","created":"2022-04-07","cited_by_count":107},{"id":"2303.17569","title":"Iterative Prompt Learning for Unsupervised Backlit Image Enhancement","created":"2023-03-30","cited_by_count":107},{"id":"1904.04346","title":"What and How Well You Performed? A Multitask Learning Approach to Action Quality Assessment","created":"2019-04-08","cited_by_count":100},{"id":"2403.16182","title":"EgoExoLearn: A Dataset for Bridging Asynchronous Ego- and Exo-centric View of Procedural Activities in Real World","created":"2024-03-24","cited_by_count":95},{"id":"1907.01172","title":"Procedure Planning in Instructional Videos","created":"2019-07-02","cited_by_count":92},{"id":"1611.05125","title":"Learning To Score Olympic Events","created":"2016-11-16","cited_by_count":88},{"id":"2201.10990","title":"Learning To Recognize Procedural Activities with Distant Supervision","created":"2022-01-26","cited_by_count":85},{"id":"2204.02968","title":"Temporal Alignment Networks for Long-term Video","created":"2022-04-06","cited_by_count":84},{"id":"2006.07665","title":"Uncertainty-aware Score Distribution Learning for Action Quality Assessment","created":"2020-06-13","cited_by_count":80},{"id":"1812.06367","title":"Action Quality Assessment Across Multiple Actions","created":"2018-12-15","cited_by_count":79},{"id":"1707.04818","title":"RED: Reinforced Encoder-Decoder Networks for Action Anticipation","created":"2017-07-16","cited_by_count":78},{"id":"2108.07797","title":"Group-aware Contrastive Regression for Action Quality Assessment","created":"2021-08-17","cited_by_count":75},{"id":"1802.02774","title":"Learning to score the figure skating sports videos","created":"2018-02-08","cited_by_count":73},{"id":"1812.05538","title":"The Pros and Cons: Rank-aware Temporal Attention for Skill Determination in Long Videos","created":"2018-12-13","cited_by_count":69},{"id":"2301.02311","title":"HierVL: Learning Hierarchical Video-Language Embeddings","created":"2023-01-05","cited_by_count":66},{"id":"2303.15786","title":"HOICLIP: Efficient Knowledge Transfer for HOI Detection with Vision-Language Models","created":"2023-03-28","cited_by_count":61},{"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},{"id":"1712.09184","title":"Detect-and-Track: Efficient Pose Estimation in Videos","created":"2017-12-26","cited_by_count":51},{"id":"2303.18230","title":"Procedure-Aware Pretraining for Instructional Video Understanding","created":"2023-03-31","cited_by_count":48},{"id":"2303.17839","title":"Learning Procedure-aware Video Representation from Instructional Videos and Their Narrations","created":"2023-03-31","cited_by_count":46},{"id":"1611.05365","title":"Am I a Baller? Basketball Performance Assessment from First-Person Videos","created":"2016-11-16","cited_by_count":40},{"id":"1906.04016","title":"Learning Temporal Pose Estimation from Sparsely-Labeled Videos","created":"2019-06-06","cited_by_count":39},{"id":"2307.08763","title":"Video-Mined Task Graphs for Keystep Recognition in Instructional Videos","created":"2023-07-17","cited_by_count":35},{"id":"2404.05029","title":"LOGO: A Long-Form Video Dataset for Group Action Quality Assessment","created":"2024-04-07","cited_by_count":31},{"id":"2206.01038","title":"A Survey on Video Action Recognition in Sports: Datasets, Methods and Applications","created":"2022-06-02","cited_by_count":28},{"id":"2407.08101","title":"What to Say and When to Say it: Live Fitness Coaching as a Testbed for Situated Interaction","created":"2024-07-11","cited_by_count":18},{"id":"2408.00672","title":"ExpertAF: Expert Actionable Feedback from Video","created":"2024-08-01","cited_by_count":17},{"id":"2503.20781","title":"BASKET: A Large-Scale Video Dataset for Fine-Grained Skill Estimation","created":"2025-03-26","cited_by_count":17},{"id":"2404.01889","title":"RAVE: Residual Vector Embedding for CLIP-Guided Backlit Image Enhancement","created":"2024-04-02","cited_by_count":11},{"id":"2404.16222","title":"Step Differences in Instructional Video","created":"2024-04-24","cited_by_count":11},{"id":"2506.06277","title":"ExAct: A Video-Language Benchmark for Expert Action Analysis","created":"2025-06-06","cited_by_count":8},{"id":"2401.01823","title":"Detours for Navigating Instructional Videos","created":"2024-01-03","cited_by_count":7},{"id":"2301.02307","title":"What You Say Is What You Show: Visual Narration Detection in Instructional Videos","created":"2023-01-05","cited_by_count":5},{"id":"2511.13993","title":"Learning Skill-Attributes for Transferable Assessment in Video","created":"2025-11-17","cited_by_count":4},{"id":"1705.07884","title":"Facial Affect Estimation in the Wild Using Deep Residual and Convolutional Networks","created":"2017-05-22","cited_by_count":2}],"next_cursor":null}