{"list":"other","total":65,"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":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"1611.07004","title":"Image-to-Image Translation with Conditional Adversarial Networks","created":"2016-11-21","cited_by_count":4527},{"id":"2012.09841","title":"Taming Transformers for High-Resolution Image Synthesis","created":"2020-12-17","cited_by_count":3253},{"id":"1802.02611","title":"Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation","created":"2018-02-07","cited_by_count":3223},{"id":"1603.08155","title":"Perceptual Losses for Real-Time Style Transfer and Super-Resolution","created":"2016-03-27","cited_by_count":2694},{"id":"2102.12122","title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","created":"2021-02-24","cited_by_count":1962},{"id":"2108.10257","title":"SwinIR: Image Restoration Using Swin Transformer","created":"2021-08-23","cited_by_count":1887},{"id":"1506.02025","title":"Spatial Transformer Networks","created":"2015-06-05","cited_by_count":1429},{"id":"2012.15840","title":"Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers","created":"2020-12-31","cited_by_count":1369},{"id":"2111.09883","title":"Swin Transformer V2: Scaling Up Capacity and Resolution","created":"2021-11-18","cited_by_count":1228},{"id":"2105.05537","title":"Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentation","created":"2021-05-12","cited_by_count":1222},{"id":"1711.11585","title":"High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs","created":"2017-11-30","cited_by_count":1179},{"id":"1611.08050","title":"Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields","created":"2016-11-24","cited_by_count":1064},{"id":"2103.15808","title":"CvT: Introducing Convolutions to Vision Transformers","created":"2021-03-29","cited_by_count":947},{"id":"2012.00364","title":"Pre-Trained Image Processing Transformer","created":"2020-12-01","cited_by_count":893},{"id":"1712.06584","title":"End-to-end Recovery of Human Shape and Pose","created":"2017-12-18","cited_by_count":885},{"id":"2106.03106","title":"Uformer: A General U-Shaped Transformer for Image Restoration","created":"2021-06-06","cited_by_count":866},{"id":"2103.14899","title":"CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification","created":"2021-03-27","cited_by_count":806},{"id":"2109.07161","title":"Resolution-robust Large Mask Inpainting with Fourier Convolutions","created":"2021-09-15","cited_by_count":738},{"id":"2205.13535","title":"AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition","created":"2022-05-26","cited_by_count":719},{"id":"2003.00196","title":"First Order Motion Model for Image Animation","created":"2020-02-29","cited_by_count":704},{"id":"1802.00434","title":"DensePose: Dense Human Pose Estimation In The Wild","created":"2018-02-01","cited_by_count":575},{"id":"2107.00652","title":"CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windows","created":"2021-07-01","cited_by_count":527},{"id":"1508.06576","title":"A Neural Algorithm of Artistic Style","created":"2015-08-26","cited_by_count":483},{"id":"1808.06601","title":"Video-to-Video Synthesis","created":"2018-08-20","cited_by_count":390},{"id":"2202.07800","title":"Not All Patches are What You Need: Expediting Vision Transformers via Token Reorganizations","created":"2022-02-16","cited_by_count":363},{"id":"1808.07371","title":"Everybody Dance Now","created":"2018-08-22","cited_by_count":315},{"id":"1905.08233","title":"Few-Shot Adversarial Learning of Realistic Neural Talking Head Models","created":"2019-05-20","cited_by_count":284},{"id":"2104.11280","title":"Motion Representations for Articulated Animation","created":"2021-04-22","cited_by_count":255},{"id":"1705.09368","title":"Pose Guided Person Image Generation","created":"2017-05-25","cited_by_count":251},{"id":"1705.02894","title":"Geometric GAN","created":"2017-05-08","cited_by_count":233},{"id":"2203.14367","title":"Thin-Plate Spline Motion Model for Image Animation","created":"2022-03-27","cited_by_count":210},{"id":"1812.08861","title":"Animating Arbitrary Objects via Deep Motion Transfer","created":"2018-12-20","cited_by_count":208},{"id":"1910.12713","title":"Few-shot Video-to-Video Synthesis","created":"2019-10-28","cited_by_count":197},{"id":"1909.12224","title":"Liquid Warping GAN: A Unified Framework for Human Motion Imitation, Appearance Transfer and Novel View Synthesis","created":"2019-09-26","cited_by_count":161},{"id":"2103.14031","title":"High-Fidelity Pluralistic Image Completion with Transformers","created":"2021-03-25","cited_by_count":134},{"id":"1804.04694","title":"A Variational U-Net for Conditional Appearance and Shape Generation","created":"2018-04-12","cited_by_count":124},{"id":"2106.03650","title":"Shuffle Transformer: Rethinking Spatial Shuffle for Vision Transformer","created":"2021-06-07","cited_by_count":115},{"id":"2107.04589","title":"ViTGAN: Training GANs with Vision Transformers","created":"2021-07-09","cited_by_count":110},{"id":"2103.10022","title":"Generating Diverse Structure for Image Inpainting With Hierarchical VQ-VAE","created":"2021-03-18","cited_by_count":106},{"id":"2007.06929","title":"Rethinking Image Inpainting via a Mutual Encoder-Decoder with Feature Equalizations","created":"2020-07-14","cited_by_count":102},{"id":"2003.00696","title":"Deep Image Spatial Transformation for Person Image Generation","created":"2020-03-02","cited_by_count":100},{"id":"1712.02621","title":"Disentangled Person Image Generation","created":"2017-12-07","cited_by_count":98},{"id":"1804.07739","title":"Synthesizing Images of Humans in Unseen Poses","created":"2018-04-20","cited_by_count":97},{"id":"1905.12384","title":"Coherent Semantic Attention for Image Inpainting","created":"2019-05-29","cited_by_count":97},{"id":"1809.01995","title":"Dense Pose Transfer","created":"2018-09-06","cited_by_count":83},{"id":"1802.00977","title":"Pose Flow: Efficient Online Pose Tracking","created":"2018-02-03","cited_by_count":80},{"id":"2105.02201","title":"PD-GAN: Probabilistic Diverse GAN for Image Inpainting","created":"2021-05-05","cited_by_count":80},{"id":"1905.08776","title":"Textured Neural Avatars","created":"2019-05-21","cited_by_count":65},{"id":"1810.11610","title":"Soft-Gated Warping-GAN for Pose-Guided Person Image Synthesis","created":"2018-10-27","cited_by_count":59},{"id":"2109.02563","title":"3D Human Texture Estimation from a Single Image with Transformers","created":"2021-09-06","cited_by_count":35},{"id":"2110.05340","title":"Revitalizing CNN Attentions via Transformers in Self-Supervised Visual Representation Learning","created":"2021-10-11","cited_by_count":34},{"id":"2204.05018","title":"Structure-Aware Motion Transfer with Deformable Anchor Model","created":"2022-04-11","cited_by_count":34},{"id":"2103.12723","title":"DeFLOCNet: Deep Image Editing via Flexible Low-level Controls","created":"2021-03-23","cited_by_count":26},{"id":"2210.07883","title":"One Model to Edit Them All: Free-Form Text-Driven Image Manipulation with Semantic Modulations","created":"2022-10-14","cited_by_count":24},{"id":"2103.14338","title":"Few-Shot Human Motion Transfer by Personalized Geometry and Texture Modeling","created":"2021-03-26","cited_by_count":21},{"id":"2106.02514","title":"The Image Local Autoregressive Transformer","created":"2021-06-04","cited_by_count":14},{"id":"2012.01158","title":"Single-Shot Freestyle Dance Reenactment","created":"2020-12-02","cited_by_count":10},{"id":"2108.01823","title":"Combining Attention with Flow for Person Image Synthesis","created":"2021-08-04","cited_by_count":9}],"next_cursor":null}