{"list":"other","total":55,"rows":[{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"1412.6550","title":"FitNets: Hints for Thin Deep Nets","created":"2014-12-19","cited_by_count":1653},{"id":"2102.05095","title":"Is Space-Time Attention All You Need for Video Understanding?","created":"2021-02-09","cited_by_count":1620},{"id":"2004.04730","title":"X3D: Expanding Architectures for Efficient Video Recognition","created":"2020-04-09","cited_by_count":637},{"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":"1906.03609","title":"Distilling Object Detectors with Fine-grained Feature Imitation","created":"2019-06-09","cited_by_count":189},{"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},{"id":"1912.04487","title":"Listen to Look: Action Recognition by Previewing Audio","created":"2019-12-10","cited_by_count":163},{"id":"1904.04289","title":"SCSampler: Sampling Salient Clips from Video for Efficient Action Recognition","created":"2019-04-08","cited_by_count":134},{"id":"2307.05463","title":"EgoVLPv2: Egocentric Video-Language Pre-training with Fusion in the Backbone","created":"2023-07-11","cited_by_count":130},{"id":"2204.03646","title":"FineDiving: A Fine-grained Dataset for Procedure-aware Action Quality Assessment","created":"2022-04-07","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":"2204.09443","title":"GIMO: Gaze-Informed Human Motion Prediction in Context","created":"2022-04-20","cited_by_count":81},{"id":"2006.07665","title":"Uncertainty-aware Score Distribution Learning for Action Quality Assessment","created":"2020-06-13","cited_by_count":80},{"id":"1803.09125","title":"Predicting Gaze in Egocentric Video by Learning Task-dependent Attention Transition","created":"2018-03-24","cited_by_count":78},{"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":"2006.00626","title":"In the Eye of the Beholder: Gaze and Actions in First Person Video","created":"2020-05-31","cited_by_count":69},{"id":"1903.02306","title":"Video-based surgical skill assessment using 3D convolutional neural networks","created":"2019-03-06","cited_by_count":57},{"id":"1901.01874","title":"Mutual Context Network for Jointly Estimating Egocentric Gaze and Actions","created":"2019-01-07","cited_by_count":54},{"id":"2208.04464","title":"In the Eye of Transformer: Global-Local Correlation for Egocentric Gaze Estimation","created":"2022-08-08","cited_by_count":51},{"id":"2112.03596","title":"E$^2$(GO)MOTION: Motion Augmented Event Stream for Egocentric Action Recognition","created":"2021-12-07","cited_by_count":50},{"id":"2502.07411","title":"EgoTextVQA: Towards Egocentric Scene-Text Aware Video Question Answering","created":"2025-02-11","cited_by_count":44},{"id":"2011.03920","title":"Integrating Human Gaze into Attention for Egocentric Activity Recognition","created":"2020-11-08","cited_by_count":42},{"id":"1611.05365","title":"Am I a Baller? Basketball Performance Assessment from First-Person Videos","created":"2016-11-16","cited_by_count":40},{"id":"2303.04439","title":"A Light Weight Model for Active Speaker Detection","created":"2023-03-08","cited_by_count":40},{"id":"2301.02217","title":"EgoDistill: Egocentric Head Motion Distillation for Efficient Video Understanding","created":"2023-01-05","cited_by_count":32},{"id":"2404.05029","title":"LOGO: A Long-Form Video Dataset for Group Action Quality Assessment","created":"2024-04-07","cited_by_count":31},{"id":"2202.14019","title":"Domain Knowledge-Informed Self-Supervised Representations for Workout Form Assessment","created":"2022-02-28","cited_by_count":25},{"id":"2405.06887","title":"FineParser: A Fine-grained Spatio-temporal Action Parser for Human-centric Action Quality Assessment","created":"2024-05-11","cited_by_count":25},{"id":"2509.07447","title":"In the Eye of MLLM: Benchmarking Egocentric Video Intent Understanding with Gaze-Guided Prompting","created":"2025-09-09","cited_by_count":22},{"id":"2503.08221","title":"EgoBlind: Towards Egocentric Visual Assistance for the Blind","created":"2025-03-11","cited_by_count":21},{"id":"2305.03907","title":"Listen to Look into the Future: Audio-Visual Egocentric Gaze Anticipation","created":"2023-05-06","cited_by_count":20},{"id":"2402.09444","title":"Multimodal Action Quality Assessment","created":"2024-01-31","cited_by_count":20},{"id":"2404.14471","title":"Narrative Action Evaluation with Prompt-Guided Multimodal Interaction","created":"2024-04-22","cited_by_count":19},{"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":"2503.20781","title":"BASKET: A Large-Scale Video Dataset for Fine-Grained Skill Estimation","created":"2025-03-26","cited_by_count":17},{"id":"2101.04884","title":"Piano Skills Assessment","created":"2021-01-13","cited_by_count":16},{"id":"2401.17217","title":"GazeGPT: Augmenting Human Capabilities using Gaze-contingent Contextual AI for Smart Eyewear","created":"2024-01-30","cited_by_count":16},{"id":"2406.08379","title":"Gazing Into Missteps: Leveraging Eye-Gaze for Unsupervised Mistake Detection in Egocentric Videos of Skilled Human Activities","created":"2024-06-12","cited_by_count":15},{"id":"2503.07860","title":"Video Action Differencing","created":"2025-03-10","cited_by_count":14},{"id":"2408.02138","title":"RICA2: Rubric-Informed, Calibrated Assessment of Actions","created":"2024-08-04","cited_by_count":13},{"id":"2506.00717","title":"Vid2Coach: Transforming How-To Videos into Task Assistants","created":"2025-05-31","cited_by_count":12},{"id":"2502.20879","title":"egoPPG: Heart Rate Estimation from Eye-Tracking Cameras in Egocentric Systems to Benefit Downstream Vision Tasks","created":"2025-02-28","cited_by_count":11},{"id":"1801.04457","title":"PrivacEye: Privacy-Preserving Head-Mounted Eye Tracking Using Egocentric Scene Image and Eye Movement Features","created":"2018-01-13","cited_by_count":8},{"id":"2301.02184","title":"Chat2Map: Efficient Scene Mapping from Multi-Ego Conversations","created":"2023-01-04","cited_by_count":8},{"id":"2506.06277","title":"ExAct: A Video-Language Benchmark for Expert Action Analysis","created":"2025-06-06","cited_by_count":8},{"id":"2505.08665","title":"SkillFormer: Unified Multi-View Video Understanding for Proficiency Estimation","created":"2025-05-13","cited_by_count":6},{"id":"2508.01915","title":"EgoTrigger: Toward Audio-Driven Image Capture for Human Memory Enhancement in All-Day Energy-Efficient Smart Glasses","created":"2025-08-03","cited_by_count":6},{"id":"2404.07347","title":"Gaze-Guided Graph Neural Network for Action Anticipation Conditioned on Intention","created":"2024-04-10","cited_by_count":5},{"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},{"id":"2501.10547","title":"HyperCam: Low-Power Onboard Computer Vision for IoT Cameras","created":"2025-01-17","cited_by_count":2}],"next_cursor":null}