{"list":"other","total":52,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"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":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2011.13456","title":"Score-Based Generative Modeling through Stochastic Differential Equations","created":"2020-11-26","cited_by_count":9122},{"id":"2105.05233","title":"Diffusion Models Beat GANs on Image Synthesis","created":"2021-05-11","cited_by_count":8255},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1503.03585","title":"Deep Unsupervised Learning using Nonequilibrium Thermodynamics","created":"2015-03-12","cited_by_count":7058},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"1706.02413","title":"PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space","created":"2017-06-07","cited_by_count":4401},{"id":"2112.10741","title":"GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models","created":"2021-12-20","cited_by_count":3614},{"id":"1512.03012","title":"ShapeNet: An Information-Rich 3D Model Repository","created":"2015-12-09","cited_by_count":2897},{"id":"1812.03828","title":"Occupancy Networks: Learning 3D Reconstruction in Function Space","created":"2018-12-10","cited_by_count":2041},{"id":"2103.13415","title":"Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields","created":"2021-03-24","cited_by_count":1964},{"id":"2012.02190","title":"pixelNeRF: Neural Radiance Fields from One or Few Images","created":"2020-12-03","cited_by_count":1584},{"id":"2212.08051","title":"Objaverse: A Universe of Annotated 3D Objects","created":"2022-12-15","cited_by_count":1540},{"id":"2011.00931","title":"Point Transformer","created":"2020-11-02","cited_by_count":1470},{"id":"2009.09761","title":"DiffWave: A Versatile Diffusion Model for Audio Synthesis","created":"2020-09-21","cited_by_count":1354},{"id":"2101.11986","title":"Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet","created":"2021-01-28","cited_by_count":1101},{"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":"2007.11571","title":"Neural Sparse Voxel Fields","created":"2020-07-22","cited_by_count":959},{"id":"2111.14819","title":"Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling","created":"2021-11-29","cited_by_count":653},{"id":"1804.01654","title":"Pixel2Mesh: Generating 3D Mesh Models from Single RGB Images","created":"2018-04-05","cited_by_count":651},{"id":"2301.00704","title":"Muse: Text-To-Image Generation via Masked Generative Transformers","created":"2023-01-02","cited_by_count":648},{"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":"2107.03502","title":"CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputation","created":"2021-07-07","cited_by_count":582},{"id":"2104.03670","title":"3D Shape Generation and Completion through Point-Voxel Diffusion","created":"2021-04-08","cited_by_count":516},{"id":"2209.12152","title":"All are Worth Words: A ViT Backbone for Diffusion Models","created":"2022-09-25","cited_by_count":502},{"id":"2203.06604","title":"Masked Autoencoders for Point Cloud Self-supervised Learning","created":"2022-03-13","cited_by_count":459},{"id":"2111.15640","title":"Diffusion Autoencoders: Toward a Meaningful and Decodable Representation","created":"2021-11-30","cited_by_count":449},{"id":"2105.06337","title":"Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speech","created":"2021-05-13","cited_by_count":447},{"id":"1905.03678","title":"What Do Single-view 3D Reconstruction Networks Learn?","created":"2019-05-09","cited_by_count":260},{"id":"2212.07388","title":"NoPe-NeRF: Optimising Neural Radiance Field with No Pose Prior","created":"2022-12-14","cited_by_count":235},{"id":"1901.11153","title":"Pix2Vox: Context-aware 3D Reconstruction from Single and Multi-view Images","created":"2019-01-31","cited_by_count":164},{"id":"2203.11183","title":"Masked Discrimination for Self-Supervised Learning on Point Clouds","created":"2022-03-21","cited_by_count":155},{"id":"1909.00321","title":"Deep Mesh Reconstruction from Single RGB Images via Topology Modification Networks","created":"2019-09-01","cited_by_count":106},{"id":"1908.01491","title":"Pixel2Mesh++: Multi-View 3D Mesh Generation via Deformation","created":"2019-08-05","cited_by_count":103},{"id":"2111.11755","title":"Guided-TTS: A Diffusion Model for Text-to-Speech via Classifier Guidance","created":"2021-11-23","cited_by_count":84},{"id":"2006.12250","title":"Pix2Vox++: Multi-scale Context-aware 3D Object Reconstruction from Single and Multiple Images","created":"2020-06-22","cited_by_count":79},{"id":"2202.02703","title":"Multi-modal Sensor Fusion for Auto Driving Perception: A Survey","created":"2022-02-06","cited_by_count":76},{"id":"2203.15190","title":"3D Shape Reconstruction from 2D Images with Disentangled Attribute Flow","created":"2022-03-29","cited_by_count":45},{"id":"1808.00758","title":"Robust Attentional Aggregation of Deep Feature Sets for Multi-view 3D Reconstruction","created":"2018-08-02","cited_by_count":44},{"id":"2205.13281","title":"Surround-view Fisheye Camera Perception for Automated Driving: Overview, Survey and Challenges","created":"2022-05-26","cited_by_count":34},{"id":"1809.07917","title":"Adaptive O-CNN: A Patch-based Deep Representation of 3D Shapes","created":"2018-09-21","cited_by_count":25},{"id":"2106.12102","title":"LegoFormer: Transformers for Block-by-Block Multi-view 3D Reconstruction","created":"2021-06-23","cited_by_count":25},{"id":"2204.09866","title":"Pixel2Mesh++: 3D Mesh Generation and Refinement from Multi-View Images","created":"2022-04-21","cited_by_count":21},{"id":"2205.03716","title":"A Review on Viewpoints and Path-planning for UAV-based 3D Reconstruction","created":"2022-05-07","cited_by_count":14}],"next_cursor":null}