{"list":"other","total":54,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"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":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1612.03144","title":"Feature Pyramid Networks for Object Detection","created":"2016-12-09","cited_by_count":5036},{"id":"1506.02640","title":"You Only Look Once: Unified, Real-Time Object Detection","created":"2015-06-08","cited_by_count":4852},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"1504.08083","title":"Fast R-CNN","created":"2015-04-30","cited_by_count":2933},{"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":"2203.12602","title":"VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training","created":"2022-03-23","cited_by_count":1322},{"id":"1712.07629","title":"SuperPoint: Self-Supervised Interest Point Detection and Description","created":"2017-12-20","cited_by_count":1320},{"id":"2203.03605","title":"DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection","created":"2022-03-07","cited_by_count":1319},{"id":"1804.02748","title":"Scaling Egocentric Vision: The EPIC-KITCHENS Dataset","created":"2018-04-08","cited_by_count":795},{"id":"2201.12329","title":"DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETR","created":"2022-01-28","cited_by_count":573},{"id":"2203.01305","title":"DN-DETR: Accelerate DETR Training by Introducing Query DeNoising","created":"2022-03-02","cited_by_count":488},{"id":"1901.07518","title":"Hybrid Task Cascade for Instance Segmentation","created":"2019-01-22","cited_by_count":481},{"id":"2006.06669","title":"Understanding Human Hands in Contact at Internet Scale","created":"2020-06-11","cited_by_count":281},{"id":"2106.02036","title":"Anticipative Video Transformer","created":"2021-06-03","cited_by_count":200},{"id":"2307.05463","title":"EgoVLPv2: Egocentric Video-Language Pre-training with Fusion in the Backbone","created":"2023-07-11","cited_by_count":130},{"id":"1812.04558","title":"Grounded Human-Object Interaction Hotspots from Video","created":"2018-12-11","cited_by_count":129},{"id":"1709.07326","title":"AffordanceNet: An End-to-End Deep Learning Approach for Object Affordance Detection","created":"2017-09-21","cited_by_count":128},{"id":"2005.02190","title":"Rolling-Unrolling LSTMs for Action Anticipation from First-Person Video","created":"2020-05-04","cited_by_count":120},{"id":"2001.04583","title":"EGO-TOPO: Environment Affordances from Egocentric Video","created":"2020-01-14","cited_by_count":111},{"id":"2204.01696","title":"Joint Hand Motion and Interaction Hotspots Prediction from Egocentric Videos","created":"2022-04-04","cited_by_count":111},{"id":"2308.07123","title":"An Outlook into the Future of Egocentric Vision","created":"2023-08-14","cited_by_count":84},{"id":"2010.05654","title":"The MECCANO Dataset: Understanding Human-Object Interactions from Egocentric Videos in an Industrial-like Domain","created":"2020-10-12","cited_by_count":79},{"id":"2303.09665","title":"LOCATE: Localize and Transfer Object Parts for Weakly Supervised Affordance Grounding","created":"2023-03-16","cited_by_count":64},{"id":"1904.05250","title":"Next-Active-Object prediction from Egocentric Videos","created":"2019-04-10","cited_by_count":55},{"id":"2112.09120","title":"Human Hands as Probes for Interactive Object Understanding","created":"2021-12-16","cited_by_count":52},{"id":"2211.09529","title":"InternVideo-Ego4D: A Pack of Champion Solutions to Ego4D Challenges","created":"2022-11-17","cited_by_count":48},{"id":"2102.00649","title":"Forecasting Action through Contact Representations from First Person Video","created":"2021-02-01","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":"2210.12649","title":"Anticipative Feature Fusion Transformer for Multi-Modal Action Anticipation","created":"2022-10-23","cited_by_count":41},{"id":"2211.14154","title":"Interaction Region Visual Transformer for Egocentric Action Anticipation","created":"2022-11-25","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":"2307.08243","title":"Uncertainty-aware State Space Transformer for Egocentric 3D Hand Trajectory Forecasting","created":"2023-07-17","cited_by_count":34},{"id":"2210.11566","title":"Rethinking Learning Approaches for Long-Term Action Anticipation","created":"2022-10-20","cited_by_count":29},{"id":"2108.05675","title":"Learning Visual Affordance Grounding from Demonstration Videos","created":"2021-08-12","cited_by_count":25},{"id":"2306.08713","title":"What can a cook in Italy teach a mechanic in India? Action Recognition Generalisation Over Scenarios and Locations","created":"2023-06-14","cited_by_count":25},{"id":"2107.09504","title":"Multi-Modal Temporal Convolutional Network for Anticipating Actions in Egocentric Videos","created":"2021-07-18","cited_by_count":23},{"id":"2304.03959","title":"StillFast: An End-to-End Approach for Short-Term Object Interaction Anticipation","created":"2023-04-08","cited_by_count":23},{"id":"2301.09209","title":"Summarize the Past to Predict the Future: Natural Language Descriptions of Context Boost Multimodal Object Interaction Anticipation","created":"2023-01-22","cited_by_count":21},{"id":"2309.02120","title":"Multi-label affordance mapping from egocentric vision","created":"2023-09-05","cited_by_count":18},{"id":"2308.08303","title":"Leveraging Next-Active Objects for Context-Aware Anticipation in Egocentric Videos","created":"2023-08-16","cited_by_count":16},{"id":"2406.01194","title":"AFF-ttention! Affordances and Attention models for Short-Term Object Interaction Anticipation","created":"2024-06-03","cited_by_count":14},{"id":"2303.00871","title":"Bayesian Deep Learning for Affordance Segmentation in images","created":"2023-03-02","cited_by_count":13},{"id":"1605.01679","title":"Learning Action Maps of Large Environments via First-Person Vision","created":"2016-05-05","cited_by_count":11},{"id":"2305.12953","title":"Enhancing Next Active Object-based Egocentric Action Anticipation with Guided Attention","created":"2023-05-22","cited_by_count":8}],"next_cursor":null}