{"list":"other","total":51,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"1812.04948","title":"A Style-Based Generator Architecture for Generative Adversarial Networks","created":"2018-12-12","cited_by_count":6013},{"id":"1806.07366","title":"Neural Ordinary Differential Equations","created":"2018-06-19","cited_by_count":3779},{"id":"1912.04958","title":"Analyzing and Improving the Image Quality of StyleGAN","created":"2019-12-03","cited_by_count":3588},{"id":"1606.03498","title":"Improved Techniques for Training GANs","created":"2016-06-10","cited_by_count":2970},{"id":"1703.06868","title":"Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization","created":"2017-03-20","cited_by_count":2010},{"id":"1812.01717","title":"Towards Accurate Generative Models of Video: A New Metric & Challenges","created":"2018-12-03","cited_by_count":1234},{"id":"2103.17249","title":"StyleCLIP: Text-Driven Manipulation of StyleGAN Imagery","created":"2021-03-31","cited_by_count":991},{"id":"2008.00951","title":"Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation","created":"2020-08-03","cited_by_count":727},{"id":"2104.10157","title":"VideoGPT: Video Generation using VQ-VAE and Transformers","created":"2021-04-20","cited_by_count":658},{"id":"2102.02766","title":"Designing an Encoder for StyleGAN Image Manipulation","created":"2021-02-04","cited_by_count":544},{"id":"1707.04993","title":"MoCoGAN: Decomposing Motion and Content for Video Generation","created":"2017-07-17","cited_by_count":524},{"id":"2104.00677","title":"Putting NeRF on a Diet: Semantically Consistent Few-Shot View Synthesis","created":"2021-04-01","cited_by_count":464},{"id":"2106.05744","title":"Pivotal Tuning for Latent-based Editing of Real Images","created":"2021-06-10","cited_by_count":427},{"id":"1808.06601","title":"Video-to-Video Synthesis","created":"2018-08-20","cited_by_count":390},{"id":"2101.05278","title":"GAN Inversion: A Survey","created":"2021-01-14","cited_by_count":367},{"id":"2112.14683","title":"StyleGAN-V: A Continuous Video Generator with the Price, Image Quality and Perks of StyleGAN2","created":"2021-12-29","cited_by_count":301},{"id":"2203.16194","title":"FlowFormer: A Transformer Architecture for Optical Flow","created":"2022-03-30","cited_by_count":275},{"id":"2104.11280","title":"Motion Representations for Articulated Animation","created":"2021-04-22","cited_by_count":255},{"id":"1808.00449","title":"Learning Blind Video Temporal Consistency","created":"2018-08-01","cited_by_count":253},{"id":"2007.00653","title":"Swapping Autoencoder for Deep Image Manipulation","created":"2020-07-01","cited_by_count":215},{"id":"2201.00424","title":"Splicing ViT Features for Semantic Appearance Transfer","created":"2022-01-02","cited_by_count":209},{"id":"2203.09043","title":"Latent Image Animator: Learning to Animate Images via Latent Space Navigation","created":"2022-03-17","cited_by_count":175},{"id":"2203.04036","title":"StyleHEAT: One-Shot High-Resolution Editable Talking Face Generation via Pre-trained StyleGAN","created":"2022-03-08","cited_by_count":169},{"id":"2104.15069","title":"A Good Image Generator Is What You Need for High-Resolution Video Synthesis","created":"2021-04-30","cited_by_count":163},{"id":"1912.06203","title":"ManiGAN: Text-Guided Image Manipulation","created":"2019-12-12","cited_by_count":156},{"id":"1511.06432","title":"Delving Deeper into Convolutional Networks for Learning Video Representations","created":"2015-11-19","cited_by_count":148},{"id":"2204.11823","title":"StyleGAN-Human: A Data-Centric Odyssey of Human Generation","created":"2022-04-25","cited_by_count":144},{"id":"1811.09245","title":"Train Sparsely, Generate Densely: Memory-efficient Unsupervised Training of High-resolution Temporal GAN","created":"2018-11-22","cited_by_count":120},{"id":"2103.10951","title":"Paint by Word","created":"2021-03-19","cited_by_count":107},{"id":"1502.08029","title":"Describing Videos by Exploiting Temporal Structure","created":"2015-02-27","cited_by_count":88},{"id":"2004.03677","title":"Semantic Image Manipulation Using Scene Graphs","created":"2020-04-07","cited_by_count":82},{"id":"2112.05142","title":"HairCLIP: Design Your Hair by Text and Reference Image","created":"2021-12-09","cited_by_count":80},{"id":"2201.08361","title":"Stitch it in Time: GAN-Based Facial Editing of Real Videos","created":"2022-01-20","cited_by_count":68},{"id":"2106.11895","title":"A Latent Transformer for Disentangled Face Editing in Images and Videos","created":"2021-06-22","cited_by_count":67},{"id":"2201.13433","title":"Third Time's the Charm? Image and Video Editing with StyleGAN3","created":"2022-01-31","cited_by_count":54},{"id":"2008.02792","title":"CaSPR: Learning Canonical Spatiotemporal Point Cloud Representations","created":"2020-08-06","cited_by_count":51},{"id":"2107.07224","title":"StyleVideoGAN: A Temporal Generative Model using a Pretrained StyleGAN","created":"2021-07-15","cited_by_count":47},{"id":"2203.07293","title":"InsetGAN for Full-Body Image Generation","created":"2022-03-14","cited_by_count":45},{"id":"2010.08188","title":"Vid-ODE: Continuous-Time Video Generation with Neural Ordinary Differential Equation","created":"2020-10-16","cited_by_count":40},{"id":"1905.10994","title":"ODE$^2$VAE: Deep generative second order ODEs with Bayesian neural networks","created":"2019-05-27","cited_by_count":36},{"id":"2112.00007","title":"Sound-Guided Semantic Image Manipulation","created":"2021-11-30","cited_by_count":35},{"id":"2205.05072","title":"Learning Visual Styles from Audio-Visual Associations","created":"2022-05-10","cited_by_count":22},{"id":"2101.03049","title":"InMoDeGAN: Interpretable Motion Decomposition Generative Adversarial Network for Video Generation","created":"2021-01-08","cited_by_count":18},{"id":"2208.07862","title":"StyleFaceV: Face Video Generation via Decomposing and Recomposing Pretrained StyleGAN3","created":"2022-08-16","cited_by_count":11},{"id":"2109.03292","title":"Simple Video Generation using Neural ODEs","created":"2021-09-07","cited_by_count":9},{"id":"2205.13996","title":"Video2StyleGAN: Disentangling Local and Global Variations in a Video","created":"2022-05-27","cited_by_count":8},{"id":"2211.02980","title":"Disentangling Content and Motion for Text-Based Neural Video Manipulation","created":"2022-11-05","cited_by_count":1}],"next_cursor":null}