{"list":"other","total":74,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"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":"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":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"id":"1611.07004","title":"Image-to-Image Translation with Conditional Adversarial Networks","created":"2016-11-21","cited_by_count":4527},{"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":"2111.05826","title":"Palette: Image-to-Image Diffusion Models","created":"2021-11-10","cited_by_count":1300},{"id":"1812.07035","title":"On the Continuity of Rotation Representations in Neural Networks","created":"2018-12-17","cited_by_count":1214},{"id":"1803.02155","title":"Self-Attention with Relative Position Representations","created":"2018-03-06","cited_by_count":1120},{"id":"2108.12409","title":"Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation","created":"2021-08-27","cited_by_count":1103},{"id":"2006.09011","title":"Improved Techniques for Training Score-Based Generative Models","created":"2020-06-16","cited_by_count":1043},{"id":"1603.09382","title":"Deep Networks with Stochastic Depth","created":"2016-03-30","cited_by_count":979},{"id":"2111.14818","title":"Blended Diffusion for Text-driven Editing of Natural Images","created":"2021-11-29","cited_by_count":927},{"id":"2108.02938","title":"ILVR: Conditioning Method for Denoising Diffusion Probabilistic Models","created":"2021-08-06","cited_by_count":635},{"id":"1806.03589","title":"Free-Form Image Inpainting with Gated Convolution","created":"2018-06-10","cited_by_count":594},{"id":"1906.05909","title":"Stand-Alone Self-Attention in Vision Models","created":"2019-06-13","cited_by_count":542},{"id":"2104.05670","title":"Action-Conditioned 3D Human Motion Synthesis with Transformer VAE","created":"2021-04-12","cited_by_count":501},{"id":"2204.14109","title":"TEMOS: Generating diverse human motions from textual descriptions","created":"2022-04-25","cited_by_count":492},{"id":"2007.15240","title":"Action2Motion: Conditioned Generation of 3D Human Motions","created":"2020-07-30","cited_by_count":441},{"id":"2203.08063","title":"MotionCLIP: Exposing Human Motion Generation to CLIP Space","created":"2022-03-15","cited_by_count":408},{"id":"1905.01164","title":"SinGAN: Learning a Generative Model from a Single Natural Image","created":"2019-05-02","cited_by_count":348},{"id":"2211.10658","title":"EDGE: Editable Dance Generation From Music","created":"2022-11-19","cited_by_count":287},{"id":"1907.01108","title":"Language2Pose: Natural Language Grounded Pose Forecasting","created":"2019-07-02","cited_by_count":257},{"id":"2102.04942","title":"Robust Motion In-betweening","created":"2021-02-09","cited_by_count":229},{"id":"1604.04382","title":"Precomputed Real-Time Texture Synthesis with Markovian Generative Adversarial Networks","created":"2016-04-15","cited_by_count":192},{"id":"2003.08386","title":"DLow: Diversifying Latent Flows for Diverse Human Motion Prediction","created":"2020-03-18","cited_by_count":185},{"id":"1711.09561","title":"HP-GAN: Probabilistic 3D human motion prediction via GAN","created":"2017-11-27","cited_by_count":176},{"id":"2005.05732","title":"Skeleton-Aware Networks for Deep Motion Retargeting","created":"2020-05-12","cited_by_count":124},{"id":"2012.00619","title":"We are More than Our Joints: Predicting how 3D Bodies Move","created":"2020-12-01","cited_by_count":115},{"id":"1812.05478","title":"Human Motion Prediction via Spatio-Temporal Inpainting","created":"2018-12-13","cited_by_count":114},{"id":"2101.11101","title":"Text2Gestures: A Transformer-Based Network for Generating Emotive Body Gestures for Virtual Agents","created":"2021-01-26","cited_by_count":106},{"id":"1910.09070","title":"Structured Prediction Helps 3D Human Motion Modelling","created":"2019-10-20","cited_by_count":96},{"id":"2005.05751","title":"Unpaired Motion Style Transfer from Video to Animation","created":"2020-05-12","cited_by_count":94},{"id":"1804.05653","title":"Neural Kinematic Networks for Unsupervised Motion Retargetting","created":"2018-04-16","cited_by_count":88},{"id":"2003.11512","title":"Improved Techniques for Training Single-Image GANs","created":"2020-03-25","cited_by_count":78},{"id":"1904.13132","title":"A critical analysis of self-supervision, or what we can learn from a single image","created":"2019-04-30","cited_by_count":76},{"id":"2010.11531","title":"Convolutional Autoencoders for Human Motion Infilling","created":"2020-10-22","cited_by_count":73},{"id":"2012.05217","title":"Positional Encoding as Spatial Inductive Bias in GANs","created":"2020-12-09","cited_by_count":69},{"id":"2206.03287","title":"NeMF: Neural Motion Fields for Kinematic Animation","created":"2022-06-04","cited_by_count":68},{"id":"1908.07007","title":"Boundless: Generative Adversarial Networks for Image Extension","created":"2019-08-19","cited_by_count":62},{"id":"2104.03963","title":"InfinityGAN: Towards Infinite-Pixel Image Synthesis","created":"2021-04-08","cited_by_count":61},{"id":"2203.13694","title":"Implicit Neural Representations for Variable Length Human Motion Generation","created":"2022-03-25","cited_by_count":61},{"id":"2211.16582","title":"SinDDM: A Single Image Denoising Diffusion Model","created":"2022-11-29","cited_by_count":60},{"id":"2103.00776","title":"Single-Shot Motion Completion with Transformer","created":"2021-03-01","cited_by_count":59},{"id":"2206.08010","title":"MoDi: Unconditional Motion Synthesis from Diverse Data","created":"2022-06-16","cited_by_count":59},{"id":"2111.12159","title":"Rhythm is a Dancer: Music-Driven Motion Synthesis with Global Structure","created":"2021-11-23","cited_by_count":53},{"id":"1810.02363","title":"Recurrent Transition Networks for Character Locomotion","created":"2018-10-04","cited_by_count":52},{"id":"2103.15545","title":"Drop the GAN: In Defense of Patches Nearest Neighbors as Single Image Generative Models","created":"2021-03-29","cited_by_count":51},{"id":"1912.10150","title":"Learning Diverse Stochastic Human-Action Generators by Learning Smooth Latent Transitions","created":"2019-12-21","cited_by_count":46},{"id":"1905.01680","title":"Learning Character-Agnostic Motion for Motion Retargeting in 2D","created":"2019-05-05","cited_by_count":45},{"id":"2211.12445","title":"SinDiffusion: Learning a Diffusion Model from a Single Natural Image","created":"2022-11-22","cited_by_count":42},{"id":"2007.01971","title":"Structure-Aware Human-Action Generation","created":"2020-07-04","cited_by_count":28},{"id":"2112.11435","title":"Learned Queries for Efficient Local Attention","created":"2021-12-21","cited_by_count":27},{"id":"2004.04634","title":"TuiGAN: Learning Versatile Image-to-Image Translation with Two Unpaired Images","created":"2020-04-09","cited_by_count":23},{"id":"2110.11191","title":"Generative Adversarial Graph Convolutional Networks for Human Action Synthesis","created":"2021-10-21","cited_by_count":23},{"id":"2010.09950","title":"Probabilistic Character Motion Synthesis using a Hierarchical Deep Latent Variable Model","created":"2020-10-20","cited_by_count":16},{"id":"2110.11460","title":"MUGL: Large Scale Multi Person Conditional Action Generation with Locomotion","created":"2021-10-21","cited_by_count":14},{"id":"2203.01488","title":"PetsGAN: Rethinking Priors for Single Image Generation","created":"2022-03-03","cited_by_count":14},{"id":"2106.07140","title":"SinIR: Efficient General Image Manipulation with Single Image Reconstruction","created":"2021-06-14","cited_by_count":13},{"id":"2105.07350","title":"ExSinGAN: Learning an Explainable Generative Model from a Single Image","created":"2021-05-16","cited_by_count":12},{"id":"1811.00818","title":"Listen to Dance: Music-driven choreography generation using Autoregressive Encoder-Decoder Network","created":"2018-11-02","cited_by_count":11},{"id":"2105.01937","title":"FLEX: Extrinsic Parameters-free Multi-view 3D Human Motion Reconstruction","created":"2021-05-05","cited_by_count":11},{"id":"2211.17260","title":"SinGRAF: Learning a 3D Generative Radiance Field for a Single Scene","created":"2022-11-30","cited_by_count":11},{"id":"2103.02997","title":"MOGAN: Morphologic-structure-aware Generative Learning from a Single Image","created":"2021-03-04","cited_by_count":9},{"id":"2103.13389","title":"Generating Novel Scene Compositions from Single Images and Videos","created":"2021-03-24","cited_by_count":8},{"id":"2005.14370","title":"Constructing Human Motion Manifold with Sequential Networks","created":"2020-05-29","cited_by_count":7}],"next_cursor":null}