{"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":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"1301.3781","title":"Efficient Estimation of Word Representations in Vector Space","created":"2013-01-16","cited_by_count":4375},{"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":"1702.04405","title":"ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes","created":"2017-02-14","cited_by_count":3117},{"id":"1504.08083","title":"Fast R-CNN","created":"2015-04-30","cited_by_count":2933},{"id":"1602.07332","title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","created":"2016-02-23","cited_by_count":2656},{"id":"2006.16241","title":"The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization","created":"2020-06-29","cited_by_count":1850},{"id":"2103.13413","title":"Vision Transformers for Dense Prediction","created":"2021-03-24","cited_by_count":1803},{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"id":"2212.08051","title":"Objaverse: A Universe of Annotated 3D Objects","created":"2022-12-15","cited_by_count":1540},{"id":"1907.07174","title":"Natural Adversarial Examples","created":"2019-07-16","cited_by_count":1408},{"id":"1709.06158","title":"Matterport3D: Learning from RGB-D Data in Indoor Environments","created":"2017-09-18","cited_by_count":1376},{"id":"2112.03857","title":"Grounded Language-Image Pre-training","created":"2021-12-07","cited_by_count":1156},{"id":"1706.04261","title":"The \"something something\" video database for learning and evaluating visual common sense","created":"2017-06-13","cited_by_count":1103},{"id":"1712.05474","title":"AI2-THOR: An Interactive 3D Environment for Visual AI","created":"2017-12-14","cited_by_count":869},{"id":"1802.08218","title":"VizWiz Grand Challenge: Answering Visual Questions from Blind People","created":"2018-02-22","cited_by_count":858},{"id":"1811.08383","title":"TSM: Temporal Shift Module for Efficient Video Understanding","created":"2018-11-20","cited_by_count":856},{"id":"1711.00199","title":"PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenes","created":"2017-11-01","cited_by_count":775},{"id":"2307.05663","title":"Objaverse-XL: A Universe of 10M+ 3D Objects","created":"2023-07-11","cited_by_count":774},{"id":"2308.11417","title":"ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenes","created":"2023-08-22","cited_by_count":764},{"id":"1804.08328","title":"Taskonomy: Disentangling Task Transfer Learning","created":"2018-04-23","cited_by_count":634},{"id":"2011.02523","title":"Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding","created":"2020-11-04","cited_by_count":604},{"id":"2109.08238","title":"Habitat-Matterport 3D Dataset (HM3D): 1000 Large-scale 3D Environments for Embodied AI","created":"2021-09-16","cited_by_count":592},{"id":"2112.12130","title":"NICE-SLAM: Neural Implicit Scalable Encoding for SLAM","created":"2021-12-22","cited_by_count":589},{"id":"1905.05055","title":"Object Detection in 20 Years: A Survey","created":"2019-05-13","cited_by_count":531},{"id":"2106.14405","title":"Habitat 2.0: Training Home Assistants to Rearrange their Habitat","created":"2021-06-28","cited_by_count":511},{"id":"1808.10654","title":"Gibson Env: Real-World Perception for Embodied Agents","created":"2018-08-31","cited_by_count":481},{"id":"2303.11331","title":"EVA-02: A Visual Representation for Neon Genesis","created":"2023-03-20","cited_by_count":381},{"id":"2206.06994","title":"ProcTHOR: Large-Scale Embodied AI Using Procedural Generation","created":"2022-06-14","cited_by_count":380},{"id":"1904.12584","title":"The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural Supervision","created":"2019-04-26","cited_by_count":372},{"id":"2110.04994","title":"Omnidata: A Scalable Pipeline for Making Multi-Task Mid-Level Vision Datasets from 3D Scans","created":"2021-10-11","cited_by_count":336},{"id":"2210.07574","title":"Is synthetic data from generative models ready for image recognition?","created":"2022-10-14","cited_by_count":320},{"id":"2009.09633","title":"3D-FUTURE: 3D Furniture shape with TextURE","created":"2020-09-21","cited_by_count":311},{"id":"2306.03514","title":"Recognize Anything: A Strong Image Tagging Model","created":"2023-06-06","cited_by_count":309},{"id":"2007.04954","title":"ThreeDWorld: A Platform for Interactive Multi-Modal Physical Simulation","created":"2020-07-09","cited_by_count":250},{"id":"2303.08131","title":"A Simple Framework for Open-Vocabulary Segmentation and Detection","created":"2023-03-14","cited_by_count":198},{"id":"2108.03272","title":"iGibson 2.0: Object-Centric Simulation for Robot Learning of Everyday Household Tasks","created":"2021-08-06","cited_by_count":194},{"id":"2108.03332","title":"BEHAVIOR: Benchmark for Everyday Household Activities in Virtual, Interactive, and Ecological Environments","created":"2021-08-06","cited_by_count":165},{"id":"2012.02924","title":"iGibson 1.0: a Simulation Environment for Interactive Tasks in Large Realistic Scenes","created":"2020-12-05","cited_by_count":155},{"id":"2210.05633","title":"Habitat-Matterport 3D Semantics Dataset","created":"2022-10-11","cited_by_count":110},{"id":"1804.09627","title":"Actor and Observer: Joint Modeling of First and Third-Person Videos","created":"2018-04-25","cited_by_count":103},{"id":"1809.00716","title":"InteriorNet: Mega-scale Multi-sensor Photo-realistic Indoor Scenes Dataset","created":"2018-09-03","cited_by_count":87},{"id":"2304.06334","title":"iDisc: Internal Discretization for Monocular Depth Estimation","created":"2023-04-13","cited_by_count":73},{"id":"2205.02961","title":"Approximate Convex Decomposition for 3D Meshes with Collision-Aware Concavity and Tree Search","created":"2022-05-05","cited_by_count":67},{"id":"2208.09480","title":"Neural Light Field Estimation for Street Scenes with Differentiable Virtual Object Insertion","created":"2022-08-19","cited_by_count":35},{"id":"2303.17590","title":"Going Beyond Nouns With Vision & Language Models Using Synthetic Data","created":"2023-03-30","cited_by_count":33},{"id":"2207.11368","title":"Neural-Sim: Learning to Generate Training Data with NeRF","created":"2022-07-22","cited_by_count":27},{"id":"2109.14718","title":"Grounding Predicates through Actions","created":"2021-09-29","cited_by_count":25},{"id":"2206.09592","title":"DALL-E for Detection: Language-driven Compositional Image Synthesis for Object Detection","created":"2022-06-20","cited_by_count":17},{"id":"2312.05277","title":"3D Copy-Paste: Physically Plausible Object Insertion for Monocular 3D Detection","created":"2023-12-08","cited_by_count":15},{"id":"2309.05956","title":"Beyond Generation: Harnessing Text to Image Models for Object Detection and Segmentation","created":"2023-09-12","cited_by_count":10},{"id":"2212.07629","title":"EM-Paste: EM-guided Cut-Paste with DALL-E Augmentation for Image-level Weakly Supervised Instance Segmentation","created":"2022-12-15","cited_by_count":4}],"next_cursor":null}