{"list":"other","total":86,"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":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"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":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"1512.03012","title":"ShapeNet: An Information-Rich 3D Model Repository","created":"2015-12-09","cited_by_count":2897},{"id":"1709.07871","title":"FiLM: Visual Reasoning with a General Conditioning Layer","created":"2017-09-22","cited_by_count":2333},{"id":"2012.07805","title":"Extracting Training Data from Large Language Models","created":"2020-12-14","cited_by_count":2189},{"id":"1812.03828","title":"Occupancy Networks: Learning 3D Reconstruction in Function Space","created":"2018-12-10","cited_by_count":2041},{"id":"2108.01073","title":"SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations","created":"2021-08-02","cited_by_count":1937},{"id":"2103.13413","title":"Vision Transformers for Dense Prediction","created":"2021-03-24","cited_by_count":1803},{"id":"2212.08051","title":"Objaverse: A Universe of Annotated 3D Objects","created":"2022-12-15","cited_by_count":1540},{"id":"1703.06907","title":"Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World","created":"2017-03-20","cited_by_count":1498},{"id":"1907.01341","title":"Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer","created":"2019-07-02","cited_by_count":1495},{"id":"2303.11328","title":"Zero-1-to-3: Zero-shot One Image to 3D Object","created":"2023-03-20","cited_by_count":1489},{"id":"2012.07421","title":"WILDS: A Benchmark of in-the-Wild Distribution Shifts","created":"2020-12-14","cited_by_count":1375},{"id":"2302.08453","title":"T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Models","created":"2023-02-16","cited_by_count":1351},{"id":"1706.07522","title":"Deep Hashing Network for Unsupervised Domain Adaptation","created":"2017-06-22","cited_by_count":1188},{"id":"1710.03077","title":"Deeper, Broader and Artier Domain Generalization","created":"2017-10-09","cited_by_count":986},{"id":"2311.04400","title":"LRM: Large Reconstruction Model for Single Image to 3D","created":"2023-11-08","cited_by_count":849},{"id":"2301.07093","title":"GLIGEN: Open-Set Grounded Text-to-Image Generation","created":"2023-01-17","cited_by_count":781},{"id":"2307.05663","title":"Objaverse-XL: A Universe of 10M+ 3D Objects","created":"2023-07-11","cited_by_count":774},{"id":"2402.05054","title":"LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation","created":"2024-02-07","cited_by_count":739},{"id":"2310.15008","title":"Wonder3D: Single Image to 3D using Cross-Domain Diffusion","created":"2023-10-23","cited_by_count":689},{"id":"2107.03342","title":"A Survey of Uncertainty in Deep Neural Networks","created":"2021-07-07","cited_by_count":680},{"id":"1804.01654","title":"Pixel2Mesh: Generating 3D Mesh Models from Single RGB Images","created":"2018-04-05","cited_by_count":651},{"id":"2012.07177","title":"Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation","created":"2020-12-13","cited_by_count":596},{"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":"2104.02008","title":"Domain Generalization with MixStyle","created":"2021-04-05","cited_by_count":566},{"id":"1610.07584","title":"Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling","created":"2016-10-24","cited_by_count":558},{"id":"2311.17043","title":"LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models","created":"2023-11-28","cited_by_count":546},{"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":"2303.07345","title":"Erasing Concepts from Diffusion Models","created":"2023-03-13","cited_by_count":539},{"id":"1903.06864","title":"Domain Generalization by Solving Jigsaw Puzzles","created":"2019-03-16","cited_by_count":450},{"id":"1910.13580","title":"Domain Generalization via Model-Agnostic Learning of Semantic Features","created":"2019-10-29","cited_by_count":407},{"id":"2110.06199","title":"ABO: Dataset and Benchmarks for Real-World 3D Object Understanding","created":"2021-10-12","cited_by_count":366},{"id":"1812.06216","title":"ABC: A Big CAD Model Dataset For Geometric Deep Learning","created":"2018-12-15","cited_by_count":341},{"id":"1803.07549","title":"Learning Category-Specific Mesh Reconstruction from Image Collections","created":"2018-03-20","cited_by_count":317},{"id":"2009.09633","title":"3D-FUTURE: 3D Furniture shape with TextURE","created":"2020-09-21","cited_by_count":311},{"id":"2007.03304","title":"Learning to Generate Novel Domains for Domain Generalization","created":"2020-07-07","cited_by_count":296},{"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":"1909.00889","title":"Domain Randomization and Pyramid Consistency: Simulation-to-Real Generalization without Accessing Target Domain Data","created":"2019-09-02","cited_by_count":246},{"id":"1902.00113","title":"Episodic Training for Domain Generalization","created":"2019-01-31","cited_by_count":245},{"id":"2403.02151","title":"TripoSR: Fast 3D Object Reconstruction from a Single Image","created":"2024-03-04","cited_by_count":232},{"id":"2006.07500","title":"Domain Generalization using Causal Matching","created":"2020-06-12","cited_by_count":225},{"id":"1804.04610","title":"Pix3D: Dataset and Methods for Single-Image 3D Shape Modeling","created":"2018-04-12","cited_by_count":218},{"id":"2403.05034","title":"CRM: Single Image to 3D Textured Mesh with Convolutional Reconstruction Model","created":"2024-03-08","cited_by_count":215},{"id":"2305.11147","title":"UniControl: A Unified Diffusion Model for Controllable Visual Generation In the Wild","created":"2023-05-18","cited_by_count":200},{"id":"2303.08133","title":"MeshDiffusion: Score-based Generative 3D Mesh Modeling","created":"2023-03-14","cited_by_count":199},{"id":"1704.06254","title":"Multi-view Supervision for Single-view Reconstruction via Differentiable Ray Consistency","created":"2017-04-20","cited_by_count":177},{"id":"1603.08637","title":"Learning a Predictable and Generative Vector Representation for Objects","created":"2016-03-29","cited_by_count":173},{"id":"2002.12212","title":"Total3DUnderstanding: Joint Layout, Object Pose and Mesh Reconstruction for Indoor Scenes from a Single Image","created":"2020-02-27","cited_by_count":172},{"id":"1904.04762","title":"Active Domain Randomization","created":"2019-04-09","cited_by_count":170},{"id":"1911.07661","title":"Domain Generalization Using a Mixture of Multiple Latent Domains","created":"2019-11-18","cited_by_count":170},{"id":"2103.02370","title":"FSDR: Frequency Space Domain Randomization for Domain Generalization","created":"2021-03-03","cited_by_count":164},{"id":"1907.04275","title":"Learning to Optimize Domain Specific Normalization for Domain Generalization","created":"2019-07-09","cited_by_count":161},{"id":"1906.02659","title":"Does Object Recognition Work for Everyone?","created":"2019-06-06","cited_by_count":151},{"id":"2211.13757","title":"Diffusion-SDF: Conditional Generative Modeling of Signed Distance Functions","created":"2022-11-24","cited_by_count":133},{"id":"1711.03129","title":"MarrNet: 3D Shape Reconstruction via 2.5D Sketches","created":"2017-11-08","cited_by_count":108},{"id":"1909.00321","title":"Deep Mesh Reconstruction from Single RGB Images via Topology Modification Networks","created":"2019-09-01","cited_by_count":106},{"id":"1810.10093","title":"Structured Domain Randomization: Bridging the Reality Gap by Context-Aware Synthetic Data","created":"2018-10-23","cited_by_count":94},{"id":"2103.06422","title":"Holistic 3D Scene Understanding from a Single Image with Implicit Representation","created":"2021-03-11","cited_by_count":94},{"id":"2007.10982","title":"Shape and Viewpoint without Keypoints","created":"2020-07-21","cited_by_count":92},{"id":"2301.08247","title":"Multiview Compressive Coding for 3D Reconstruction","created":"2023-01-19","cited_by_count":71},{"id":"2401.14398","title":"pix2gestalt: Amodal Segmentation by Synthesizing Wholes","created":"2024-01-25","cited_by_count":70},{"id":"1809.05068","title":"Learning Shape Priors for Single-View 3D Completion and Reconstruction","created":"2018-09-13","cited_by_count":68},{"id":"1812.11166","title":"Learning to Reconstruct Shapes from Unseen Classes","created":"2018-12-28","cited_by_count":60},{"id":"2207.08656","title":"Towards High-Fidelity Single-view Holistic Reconstruction of Indoor Scenes","created":"2022-07-18","cited_by_count":44},{"id":"2403.12011","title":"HOIDiffusion: Generating Realistic 3D Hand-Object Interaction Data","created":"2024-03-18","cited_by_count":37},{"id":"2312.14198","title":"ZeroShape: Regression-based Zero-shot Shape Reconstruction","created":"2023-12-21","cited_by_count":30},{"id":"2308.02552","title":"Degeneration-Tuning: Using Scrambled Grid shield Unwanted Concepts from Stable Diffusion","created":"2023-08-02","cited_by_count":27},{"id":"2204.03642","title":"Pre-train, Self-train, Distill: A simple recipe for Supersizing 3D Reconstruction","created":"2022-04-07","cited_by_count":26},{"id":"2003.08264","title":"Cross-domain Self-supervised Learning for Domain Adaptation with Few Source Labels","created":"2020-03-18","cited_by_count":24},{"id":"2305.06968","title":"HuManiFlow: Ancestor-Conditioned Normalising Flows on SO(3) Manifolds for Human Pose and Shape Distribution Estimation","created":"2023-05-11","cited_by_count":24},{"id":"2306.08103","title":"Generating Images with 3D Annotations Using Diffusion Models","created":"2023-06-13","cited_by_count":18},{"id":"2011.01891","title":"Policy Transfer via Kinematic Domain Randomization and Adaptation","created":"2020-11-03","cited_by_count":16},{"id":"2304.06247","title":"ShapeClipper: Scalable 3D Shape Learning from Single-View Images via Geometric and CLIP-based Consistency","created":"2023-04-13","cited_by_count":16},{"id":"2012.02516","title":"A Note on Data Biases in Generative Models","created":"2020-12-04","cited_by_count":13},{"id":"1903.03953","title":"Domain Randomization for Active Pose Estimation","created":"2019-03-10","cited_by_count":11},{"id":"2204.10235","title":"Planes vs. Chairs: Category-guided 3D shape learning without any 3D cues","created":"2022-04-21","cited_by_count":9},{"id":"2403.11111","title":"Diffusion Models are Efficient Data Generators for Human Mesh Recovery","created":"2024-03-17","cited_by_count":8}],"next_cursor":null}