{"list":"other","total":51,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"1612.03144","title":"Feature Pyramid Networks for Object Detection","created":"2016-12-09","cited_by_count":5036},{"id":"2303.05499","title":"Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection","created":"2023-03-09","cited_by_count":3332},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"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":"2110.06864","title":"ByteTrack: Multi-Object Tracking by Associating Every Detection Box","created":"2021-10-13","cited_by_count":823},{"id":"2009.07736","title":"HOTA: A Higher Order Metric for Evaluating Multi-Object Tracking","created":"2020-09-16","cited_by_count":552},{"id":"2006.13256","title":"Rescaling Egocentric Vision","created":"2020-06-23","cited_by_count":540},{"id":"2304.08069","title":"DETRs Beat YOLOs on Real-time Object Detection","created":"2023-04-17","cited_by_count":533},{"id":"2405.14458","title":"YOLOv10: Real-Time End-to-End Object Detection","created":"2024-05-23","cited_by_count":515},{"id":"2401.17270","title":"YOLO-World: Real-Time Open-Vocabulary Object Detection","created":"2024-01-30","cited_by_count":503},{"id":"2103.17154","title":"Learning Spatio-Temporal Transformer for Visual Tracking","created":"2021-03-31","cited_by_count":350},{"id":"2206.14651","title":"BoT-SORT: Robust Associations Multi-Pedestrian Tracking","created":"2022-06-29","cited_by_count":320},{"id":"2202.07925","title":"ActionFormer: Localizing Moments of Actions with Transformers","created":"2022-02-16","cited_by_count":311},{"id":"2006.06669","title":"Understanding Human Hands in Contact at Internet Scale","created":"2020-06-11","cited_by_count":281},{"id":"2403.11481","title":"VideoAgent: A Memory-augmented Multimodal Agent for Video Understanding","created":"2024-03-18","cited_by_count":229},{"id":"2308.13561","title":"Project Aria: A New Tool for Egocentric Multi-Modal AI Research","created":"2023-08-24","cited_by_count":208},{"id":"2106.02036","title":"Anticipative Video Transformer","created":"2021-06-03","cited_by_count":200},{"id":"1911.12836","title":"Siam R-CNN: Visual Tracking by Re-Detection","created":"2019-11-28","cited_by_count":174},{"id":"2005.02190","title":"Rolling-Unrolling LSTMs for Action Anticipation from First-Person Video","created":"2020-05-04","cited_by_count":120},{"id":"2003.11014","title":"Know Your Surroundings: Exploiting Scene Information for Object Tracking","created":"2020-03-24","cited_by_count":119},{"id":"2308.07123","title":"An Outlook into the Future of Egocentric Vision","created":"2023-08-14","cited_by_count":84},{"id":"1707.04818","title":"RED: Reinforced Encoder-Decoder Networks for Action Anticipation","created":"2017-07-16","cited_by_count":78},{"id":"1604.06506","title":"Online Action Detection","created":"2016-04-21","cited_by_count":69},{"id":"2209.09236","title":"Real-time Online Video Detection with Temporal Smoothing Transformers","created":"2022-09-19","cited_by_count":58},{"id":"2406.04221","title":"Matching Anything by Segmenting Anything","created":"2024-06-06","cited_by_count":50},{"id":"2211.09529","title":"InternVideo-Ego4D: A Pack of Champion Solutions to Ego4D Challenges","created":"2022-11-17","cited_by_count":48},{"id":"2311.17241","title":"End-to-End Temporal Action Detection with 1B Parameters Across 1000 Frames","created":"2023-11-28","cited_by_count":47},{"id":"2301.00746","title":"NaQ: Leveraging Narrations as Queries to Supervise Episodic Memory","created":"2023-01-02","cited_by_count":46},{"id":"2406.18070","title":"EgoVideo: Exploring Egocentric Foundation Model and Downstream Adaptation","created":"2024-06-26","cited_by_count":44},{"id":"2309.08816","title":"EgoObjects: A Large-Scale Egocentric Dataset for Fine-Grained Object Understanding","created":"2023-09-15","cited_by_count":40},{"id":"1703.07023","title":"Encouraging LSTMs to Anticipate Actions Very Early","created":"2017-03-21","cited_by_count":37},{"id":"2107.13411","title":"Predicting the Future from First Person (Egocentric) Vision: A Survey","created":"2021-07-28","cited_by_count":36},{"id":"2409.10917","title":"AMEGO: Active Memory from long EGOcentric videos","created":"2024-09-17","cited_by_count":36},{"id":"2404.05072","title":"Spatial Cognition from Egocentric Video: Out of Sight, Not Out of Mind","created":"2024-04-07","cited_by_count":28},{"id":"2301.03213","title":"EgoTracks: A Long-term Egocentric Visual Object Tracking Dataset","created":"2023-01-09","cited_by_count":27},{"id":"2209.13502","title":"Visual Object Tracking in First Person Vision","created":"2022-09-27","cited_by_count":25},{"id":"2212.06969","title":"EgoLoc: Revisiting 3D Object Localization from Egocentric Videos with Visual Queries","created":"2022-12-14","cited_by_count":25},{"id":"2211.10528","title":"Where is my Wallet? Modeling Object Proposal Sets for Egocentric Visual Query Localization","created":"2022-11-18","cited_by_count":24},{"id":"2108.13665","title":"Is First Person Vision Challenging for Object Tracking?","created":"2021-08-31","cited_by_count":21},{"id":"2306.09324","title":"Single-Stage Visual Query Localization in Egocentric Videos","created":"2023-06-15","cited_by_count":20},{"id":"2207.00383","title":"ReLER@ZJU-Alibaba Submission to the Ego4D Natural Language Queries Challenge 2022","created":"2022-07-01","cited_by_count":19},{"id":"2306.15850","title":"SpotEM: Efficient Video Search for Episodic Memory","created":"2023-06-28","cited_by_count":17},{"id":"2208.01949","title":"Negative Frames Matter in Egocentric Visual Query 2D Localization","created":"2022-08-03","cited_by_count":14},{"id":"2204.13340","title":"The Wisdom of Crowds: Temporal Progressive Attention for Early Action Prediction","created":"2022-04-28","cited_by_count":13},{"id":"2406.15778","title":"ObjectNLQ @ Ego4D Episodic Memory Challenge 2024","created":"2024-06-22","cited_by_count":10},{"id":"2309.15278","title":"Out of Sight, Still in Mind: Reasoning and Planning about Unobserved Objects with Video Tracking Enabled Memory Models","created":"2023-09-26","cited_by_count":5}],"next_cursor":null}