{"list":"other","total":54,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"1903.11027","title":"nuScenes: A multimodal dataset for autonomous driving","created":"2019-03-26","cited_by_count":4523},{"id":"1702.04405","title":"ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes","created":"2017-02-14","cited_by_count":3117},{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"id":"1803.09010","title":"Datasheets for Datasets","created":"2018-03-23","cited_by_count":1386},{"id":"1904.07850","title":"Objects as Points","created":"2019-04-16","cited_by_count":1175},{"id":"2006.11275","title":"Center-based 3D Object Detection and Tracking","created":"2020-06-19","cited_by_count":1144},{"id":"2205.13542","title":"BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation","created":"2022-05-26","cited_by_count":850},{"id":"1804.02748","title":"Scaling Egocentric Vision: The EPIC-KITCHENS Dataset","created":"2018-04-08","cited_by_count":795},{"id":"2001.04193","title":"Deep Learning for Person Re-identification: A Survey and Outlook","created":"2020-01-13","cited_by_count":549},{"id":"2106.14405","title":"Habitat 2.0: Training Home Assistants to Rearrange their Habitat","created":"2021-06-28","cited_by_count":511},{"id":"2103.17154","title":"Learning Spatio-Temporal Transformer for Visual Tracking","created":"2021-03-31","cited_by_count":350},{"id":"1904.07220","title":"Learning Discriminative Model Prediction for Tracking","created":"2019-04-15","cited_by_count":344},{"id":"2203.01577","title":"HOI4D: A 4D Egocentric Dataset for Category-Level Human-Object Interaction","created":"2022-03-03","cited_by_count":327},{"id":"2203.11082","title":"MixFormer: End-to-End Tracking with Iterative Mixed Attention","created":"2022-03-21","cited_by_count":281},{"id":"2003.12565","title":"Probabilistic Regression for Visual Tracking","created":"2020-03-27","cited_by_count":231},{"id":"1908.08498","title":"EPIC-Fusion: Audio-Visual Temporal Binding for Egocentric Action Recognition","created":"2019-08-22","cited_by_count":226},{"id":"2303.11301","title":"VoxelNeXt: Fully Sparse VoxelNet for 3D Object Detection and Tracking","created":"2023-03-20","cited_by_count":222},{"id":"2305.05658","title":"TidyBot: Personalized Robot Assistance with Large Language Models","created":"2023-05-09","cited_by_count":221},{"id":"1708.01642","title":"Cut, Paste and Learn: Surprisingly Easy Synthesis for Instance Detection","created":"2017-08-04","cited_by_count":209},{"id":"1610.02984","title":"Person Re-identification: Past, Present and Future","created":"2016-10-10","cited_by_count":181},{"id":"2306.06362","title":"Aria Digital Twin: A New Benchmark Dataset for Egocentric 3D Machine Perception","created":"2023-06-10","cited_by_count":167},{"id":"2012.09988","title":"Objectron: A Large Scale Dataset of Object-Centric Videos in the Wild with Pose Annotations","created":"2020-12-18","cited_by_count":155},{"id":"2303.10826","title":"Visual Prompt Multi-Modal Tracking","created":"2023-03-20","cited_by_count":142},{"id":"2203.11192","title":"Transforming Model Prediction for Tracking","created":"2022-03-21","cited_by_count":117},{"id":"1905.09035","title":"What Would You Expect? Anticipating Egocentric Actions with Rolling-Unrolling LSTMs and Modality Attention","created":"2019-05-22","cited_by_count":105},{"id":"1909.01871","title":"Help, Anna! Visual Navigation with Natural Multimodal Assistance via Retrospective Curiosity-Encouraging Imitation Learning","created":"2019-09-04","cited_by_count":100},{"id":"2104.14682","title":"EagerMOT: 3D Multi-Object Tracking via Sensor Fusion","created":"2021-04-29","cited_by_count":83},{"id":"1904.09882","title":"You2Me: Inferring Body Pose in Egocentric Video via First and Second Person Interactions","created":"2019-04-22","cited_by_count":82},{"id":"1902.03334","title":"Photorealistic Image Synthesis for Object Instance Detection","created":"2019-02-09","cited_by_count":66},{"id":"2112.02857","title":"PTTR: Relational 3D Point Cloud Object Tracking with Transformer","created":"2021-12-06","cited_by_count":65},{"id":"2004.00830","title":"Tracking by Instance Detection: A Meta-Learning Approach","created":"2020-04-02","cited_by_count":61},{"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":"1603.07763","title":"Seeing Invisible Poses: Estimating 3D Body Pose from Egocentric Video","created":"2016-03-24","cited_by_count":45},{"id":"1604.03196","title":"Privacy-Preserving Human Activity Recognition from Extreme Low Resolution","created":"2016-04-12","cited_by_count":43},{"id":"1612.07796","title":"First-Person Activity Forecasting with Online Inverse Reinforcement Learning","created":"2016-12-22","cited_by_count":40},{"id":"2105.12414","title":"Anticipating human actions by correlating past with the future with Jaccard similarity measures","created":"2021-05-26","cited_by_count":36},{"id":"2008.11239","title":"HoloLens 2 Research Mode as a Tool for Computer Vision Research","created":"2020-08-25","cited_by_count":34},{"id":"2201.07929","title":"Estimating Egocentric 3D Human Pose in the Wild with External Weak Supervision","created":"2022-01-20","cited_by_count":34},{"id":"2205.01652","title":"Episodic Memory Question Answering","created":"2022-05-03","cited_by_count":32},{"id":"2203.13116","title":"Egocentric Prediction of Action Target in 3D","created":"2022-03-24","cited_by_count":31},{"id":"2301.03213","title":"EgoTracks: A Long-term Egocentric Visual Object Tracking Dataset","created":"2023-01-09","cited_by_count":27},{"id":"1609.07826","title":"Multiview RGB-D Dataset for Object Instance Detection","created":"2016-09-26","cited_by_count":26},{"id":"2209.13502","title":"Visual Object Tracking in First Person Vision","created":"2022-09-27","cited_by_count":25},{"id":"2108.13665","title":"Is First Person Vision Challenging for Object Tracking?","created":"2021-08-31","cited_by_count":21},{"id":"2002.12114","title":"Domain Decluttering: Simplifying Images to Mitigate Synthetic-Real Domain Shift and Improve Depth Estimation","created":"2020-02-27","cited_by_count":17},{"id":"1604.00906","title":"Detecting Engagement in Egocentric Video","created":"2016-04-04","cited_by_count":13},{"id":"1703.09771","title":"Deep 6-DOF Tracking","created":"2017-03-28","cited_by_count":13},{"id":"1905.13586","title":"Deep Dual Relation Modeling for Egocentric Interaction Recognition","created":"2019-05-31","cited_by_count":11},{"id":"2211.02648","title":"HoloLens 2 Sensor Streaming","created":"2022-11-04","cited_by_count":11},{"id":"2308.05221","title":"Alexa, play with robot: Introducing the First Alexa Prize SimBot Challenge on Embodied AI","created":"2023-08-09","cited_by_count":5}],"next_cursor":null}