{"list":"other","total":56,"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":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"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":"2105.15203","title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","created":"2021-05-31","cited_by_count":2940},{"id":"2102.04306","title":"TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation","created":"2021-02-08","cited_by_count":1558},{"id":"2011.00931","title":"Point Transformer","created":"2020-11-02","cited_by_count":1470},{"id":"2012.15840","title":"Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers","created":"2020-12-31","cited_by_count":1369},{"id":"2105.05537","title":"Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentation","created":"2021-05-12","cited_by_count":1222},{"id":"2101.11986","title":"Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet","created":"2021-01-28","cited_by_count":1101},{"id":"2103.10504","title":"UNETR: Transformers for 3D Medical Image Segmentation","created":"2021-03-18","cited_by_count":959},{"id":"2106.03106","title":"Uformer: A General U-Shaped Transformer for Image Restoration","created":"2021-06-06","cited_by_count":866},{"id":"2105.05633","title":"Segmenter: Transformer for Semantic Segmentation","created":"2021-05-12","cited_by_count":855},{"id":"2103.14899","title":"CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification","created":"2021-03-27","cited_by_count":806},{"id":"2103.17239","title":"Going deeper with Image Transformers","created":"2021-03-31","cited_by_count":764},{"id":"2102.04378","title":"TransReID: Transformer-based Object Re-Identification","created":"2021-02-08","cited_by_count":435},{"id":"2103.15436","title":"Transformer Tracking","created":"2021-03-29","cited_by_count":412},{"id":"2102.10662","title":"Medical Transformer: Gated Axial-Attention for Medical Image Segmentation","created":"2021-02-21","cited_by_count":320},{"id":"2103.11886","title":"DeepViT: Towards Deeper Vision Transformer","created":"2021-03-22","cited_by_count":289},{"id":"2104.05707","title":"LocalViT: Analyzing Locality in Vision Transformers","created":"2021-04-12","cited_by_count":228},{"id":"2201.12288","title":"VRT: A Video Restoration Transformer","created":"2022-01-28","cited_by_count":220},{"id":"2107.14222","title":"Rethinking and Improving Relative Position Encoding for Vision Transformer","created":"2021-07-29","cited_by_count":207},{"id":"2012.11409","title":"3D Object Detection with Pointformer","created":"2020-12-21","cited_by_count":194},{"id":"2110.09784","title":"SSAST: Self-Supervised Audio Spectrogram Transformer","created":"2021-10-19","cited_by_count":169},{"id":"2106.13112","title":"VOLO: Vision Outlooker for Visual Recognition","created":"2021-06-24","cited_by_count":165},{"id":"2112.10762","title":"StyleSwin: Transformer-based GAN for High-resolution Image Generation","created":"2021-12-20","cited_by_count":152},{"id":"2201.04288","title":"Multiview Transformers for Video Recognition","created":"2022-01-12","cited_by_count":148},{"id":"2103.07976","title":"TransFG: A Transformer Architecture for Fine-grained Recognition","created":"2021-03-14","cited_by_count":132},{"id":"2103.12091","title":"Transformer-Based Attention Networks for Continuous Pixel-Wise Prediction","created":"2021-03-22","cited_by_count":125},{"id":"2103.01209","title":"Generative Adversarial Transformers","created":"2021-03-01","cited_by_count":120},{"id":"2106.04095","title":"Diverse Part Discovery: Occluded Person Re-identification with Part-Aware Transformer","created":"2021-06-08","cited_by_count":120},{"id":"2107.00781","title":"UTNet: A Hybrid Transformer Architecture for Medical Image Segmentation","created":"2021-07-02","cited_by_count":116},{"id":"2103.10206","title":"DanceFormer: Music Conditioned 3D Dance Generation with Parametric Motion Transformer","created":"2021-03-18","cited_by_count":111},{"id":"2112.04702","title":"Fast Point Transformer","created":"2021-12-09","cited_by_count":104},{"id":"2107.02612","title":"Combining EfficientNet and Vision Transformers for Video Deepfake Detection","created":"2021-07-06","cited_by_count":82},{"id":"2105.09511","title":"Medical Image Segmentation Using Squeeze-and-Expansion Transformers","created":"2021-05-20","cited_by_count":57},{"id":"2105.09447","title":"VTNet: Visual Transformer Network for Object Goal Navigation","created":"2021-05-20","cited_by_count":51},{"id":"2104.00921","title":"AAformer: Auto-Aligned Transformer for Person Re-Identification","created":"2021-04-02","cited_by_count":48},{"id":"2107.02380","title":"Learning Disentangled Representation Implicitly via Transformer for Occluded Person Re-Identification","created":"2021-07-06","cited_by_count":44},{"id":"2101.03904","title":"Trear: Transformer-based RGB-D Egocentric Action Recognition","created":"2021-01-05","cited_by_count":39},{"id":"2107.05946","title":"HAT: Hierarchical Aggregation Transformers for Person Re-identification","created":"2021-07-13","cited_by_count":39},{"id":"2105.00149","title":"SVT-Net: Super Light-Weight Sparse Voxel Transformer for Large Scale Place Recognition","created":"2021-05-01","cited_by_count":36},{"id":"2109.14483","title":"CCTrans: Simplifying and Improving Crowd Counting with Transformer","created":"2021-09-29","cited_by_count":30},{"id":"2104.01745","title":"A Video Is Worth Three Views: Trigeminal Transformers for Video-based Person Re-identification","created":"2021-04-05","cited_by_count":28},{"id":"2104.13044","title":"Dual Transformer for Point Cloud Analysis","created":"2021-04-27","cited_by_count":26},{"id":"2112.09300","title":"Towards End-to-End Image Compression and Analysis with Transformers","created":"2021-12-17","cited_by_count":26},{"id":"2106.04108","title":"Fully Transformer Networks for Semantic Image Segmentation","created":"2021-06-08","cited_by_count":24},{"id":"2107.09240","title":"Generative Video Transformer: Can Objects be the Words?","created":"2021-07-20","cited_by_count":24},{"id":"2105.04447","title":"SCTN: Sparse Convolution-Transformer Network for Scene Flow Estimation","created":"2021-05-10","cited_by_count":23},{"id":"2112.03631","title":"SSAT: A Symmetric Semantic-Aware Transformer Network for Makeup Transfer and Removal","created":"2021-12-07","cited_by_count":22},{"id":"2104.14702","title":"Pyramid Medical Transformer for Medical Image Segmentation","created":"2021-04-29","cited_by_count":20},{"id":"2110.04792","title":"6D-ViT: Category-Level 6D Object Pose Estimation via Transformer-based Instance Representation Learning","created":"2021-10-10","cited_by_count":20},{"id":"2106.03720","title":"Person Re-Identification with a Locally Aware Transformer","created":"2021-06-07","cited_by_count":19},{"id":"2103.16469","title":"Spatiotemporal Transformer for Video-based Person Re-identification","created":"2021-03-30","cited_by_count":15},{"id":"2104.13636","title":"Point Cloud Learning with Transformer","created":"2021-04-28","cited_by_count":15}],"next_cursor":null}