{"list":"other","total":69,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"1508.07909","title":"Neural Machine Translation of Rare Words with Subword Units","created":"2015-08-31","cited_by_count":2918},{"id":"1901.05103","title":"DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation","created":"2019-01-16","cited_by_count":2689},{"id":"1812.03828","title":"Occupancy Networks: Learning 3D Reconstruction in Function Space","created":"2018-12-10","cited_by_count":2041},{"id":"1504.06852","title":"FlowNet: Learning Optical Flow with Convolutional Networks","created":"2015-04-26","cited_by_count":1059},{"id":"1612.00603","title":"A Point Set Generation Network for 3D Object Reconstruction from a Single Image","created":"2016-12-02","cited_by_count":979},{"id":"1906.01618","title":"Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representations","created":"2019-06-04","cited_by_count":864},{"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":"1804.01654","title":"Pixel2Mesh: Generating 3D Mesh Models from Single RGB Images","created":"2018-04-05","cited_by_count":651},{"id":"1604.00449","title":"3D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstruction","created":"2016-04-02","cited_by_count":588},{"id":"1802.05384","title":"AtlasNet: A Papier-M\\^ach\\'e Approach to Learning 3D Surface Generation","created":"2018-02-15","cited_by_count":539},{"id":"1901.02970","title":"Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimation","created":"2019-01-09","cited_by_count":495},{"id":"2206.06994","title":"ProcTHOR: Large-Scale Embodied AI Using Procedural Generation","created":"2022-06-14","cited_by_count":380},{"id":"1701.01370","title":"Learning from Synthetic Humans","created":"2017-01-05","cited_by_count":359},{"id":"1803.07549","title":"Learning Category-Specific Mesh Reconstruction from Image Collections","created":"2018-03-20","cited_by_count":317},{"id":"1611.07700","title":"3D Menagerie: Modeling the 3D shape and pose of animals","created":"2016-11-23","cited_by_count":312},{"id":"1804.06516","title":"Training Deep Networks with Synthetic Data: Bridging the Reality Gap by Domain Randomization","created":"2018-04-18","cited_by_count":294},{"id":"2008.08465","title":"CosyPose: Consistent multi-view multi-object 6D pose estimation","created":"2020-08-19","cited_by_count":287},{"id":"2307.15055","title":"PointOdyssey: A Large-Scale Synthetic Dataset for Long-Term Point Tracking","created":"2023-07-27","cited_by_count":276},{"id":"2312.09067","title":"Holodeck: Language Guided Generation of 3D Embodied AI Environments","created":"2023-12-14","cited_by_count":268},{"id":"2212.05171","title":"ULIP: Learning a Unified Representation of Language, Images, and Point Clouds for 3D Understanding","created":"2022-12-10","cited_by_count":267},{"id":"2307.02485","title":"Building Cooperative Embodied Agents Modularly with Large Language Models","created":"2023-07-05","cited_by_count":237},{"id":"2306.16940","title":"BEDLAM: A Synthetic Dataset of Bodies Exhibiting Detailed Lifelike Animated Motion","created":"2023-06-29","cited_by_count":236},{"id":"1611.04201","title":"CAD2RL: Real Single-Image Flight without a Single Real Image","created":"2016-11-13","cited_by_count":233},{"id":"2112.12761","title":"BANMo: Building Animatable 3D Neural Models from Many Casual Videos","created":"2021-12-23","cited_by_count":197},{"id":"2311.18803","title":"BioCLIP: A Vision Foundation Model for the Tree of Life","created":"2023-11-30","cited_by_count":161},{"id":"2306.09310","title":"Infinite Photorealistic Worlds using Procedural Generation","created":"2023-06-15","cited_by_count":147},{"id":"2403.01248","title":"SceneCraft: An LLM Agent for Synthesizing 3D Scene as Blender Code","created":"2024-03-02","cited_by_count":134},{"id":"1812.05040","title":"Learning Semantic Segmentation from Synthetic Data: A Geometrically Guided Input-Output Adaptation Approach","created":"2018-12-12","cited_by_count":119},{"id":"2211.12497","title":"MagicPony: Learning Articulated 3D Animals in the Wild","created":"2022-11-22","cited_by_count":112},{"id":"1908.07201","title":"Three-D Safari: Learning to Estimate Zebra Pose, Shape, and Texture from Images \"In the Wild\"","created":"2019-08-20","cited_by_count":106},{"id":"2403.13064","title":"SceneScript: Reconstructing Scenes With An Autoregressive Structured Language Model","created":"2024-03-19","cited_by_count":96},{"id":"2310.12945","title":"3D-GPT: Procedural 3D Modeling with Large Language Models","created":"2023-10-19","cited_by_count":95},{"id":"2103.06422","title":"Holistic 3D Scene Understanding from a Single Image with Implicit Representation","created":"2021-03-11","cited_by_count":94},{"id":"1703.04670","title":"6-DoF Object Pose from Semantic Keypoints","created":"2017-03-14","cited_by_count":89},{"id":"1811.05804","title":"Creatures great and SMAL: Recovering the shape and motion of animals from video","created":"2018-11-14","cited_by_count":84},{"id":"2004.00614","title":"Articulation-aware Canonical Surface Mapping","created":"2020-04-01","cited_by_count":81},{"id":"2007.11110","title":"Who Left the Dogs Out? 3D Animal Reconstruction with Expectation Maximization in the Loop","created":"2020-07-21","cited_by_count":81},{"id":"1608.05137","title":"IM2CAD","created":"2016-08-18","cited_by_count":78},{"id":"1808.02201","title":"Holistic 3D Scene Parsing and Reconstruction from a Single RGB Image","created":"2018-08-07","cited_by_count":69},{"id":"2112.01988","title":"ROCA: Robust CAD Model Retrieval and Alignment from a Single Image","created":"2021-12-03","cited_by_count":67},{"id":"2207.03434","title":"LASSIE: Learning Articulated Shapes from Sparse Image Ensemble via 3D Part Discovery","created":"2022-07-07","cited_by_count":66},{"id":"2007.13034","title":"Mask2CAD: 3D Shape Prediction by Learning to Segment and Retrieve","created":"2020-07-26","cited_by_count":65},{"id":"2311.12631","title":"GPT4Motion: Scripting Physical Motions in Text-to-Video Generation via Blender-Oriented GPT Planning","created":"2023-11-21","cited_by_count":61},{"id":"2203.15536","title":"BARC: Learning to Regress 3D Dog Shape from Images by Exploiting Breed Information","created":"2022-03-29","cited_by_count":51},{"id":"2207.08656","title":"Towards High-Fidelity Single-view Holistic Reconstruction of Indoor Scenes","created":"2022-07-18","cited_by_count":44},{"id":"2404.11735","title":"Learning with 3D rotations, a hitchhiker's guide to SO(3)","created":"2024-04-17","cited_by_count":42},{"id":"2101.12378","title":"NeMo: Neural Mesh Models of Contrastive Features for Robust 3D Pose Estimation","created":"2021-01-29","cited_by_count":41},{"id":"2008.06133","title":"3D Bird Reconstruction: a Dataset, Model, and Shape Recovery from a Single View","created":"2020-08-13","cited_by_count":40},{"id":"2108.09368","title":"Patch2CAD: Patchwise Embedding Learning for In-the-Wild Shape Retrieval from a Single Image","created":"2021-08-20","cited_by_count":39},{"id":"2211.03568","title":"CASA: Category-agnostic Skeletal Animal Reconstruction","created":"2022-11-04","cited_by_count":35},{"id":"1604.01347","title":"Marr Revisited: 2D-3D Alignment via Surface Normal Prediction","created":"2016-04-05","cited_by_count":34},{"id":"2105.09396","title":"Birds of a Feather: Capturing Avian Shape Models from Images","created":"2021-05-19","cited_by_count":30},{"id":"2307.10455","title":"A Step Towards Worldwide Biodiversity Assessment: The BIOSCAN-1M Insect Dataset","created":"2023-07-19","cited_by_count":30},{"id":"2012.11575","title":"From Points to Multi-Object 3D Reconstruction","created":"2020-12-21","cited_by_count":29},{"id":"2003.00080","title":"Transferring Dense Pose to Proximal Animal Classes","created":"2020-02-28","cited_by_count":23},{"id":"2209.05624","title":"Robust Category-Level 6D Pose Estimation with Coarse-to-Fine Rendering of Neural Features","created":"2022-09-12","cited_by_count":23},{"id":"2404.15228","title":"Re-Thinking Inverse Graphics With Large Language Models","created":"2024-04-23","cited_by_count":23},{"id":"2206.07028","title":"Learning 3D Object Shape and Layout without 3D Supervision","created":"2022-06-14","cited_by_count":19},{"id":"1607.00598","title":"A Coarse-to-Fine Indoor Layout Estimation (CFILE) Method","created":"2016-07-03","cited_by_count":15},{"id":"1507.07646","title":"Learning 3D Deformation of Animals from 2D Images","created":"2015-07-28","cited_by_count":11},{"id":"2310.19516","title":"Generating Context-Aware Natural Answers for Questions in 3D Scenes","created":"2023-10-30","cited_by_count":5}],"next_cursor":null}