If you have any problems, suggestions or improvements, please submit the issue or PR.

• Attention
• OverallSurvey
• NLP
  • Language
  • Speech
• CV
  • Backbone_Classification
  • Self-Supervised
  • Interpretability and Robustness
  • Detection
  • HOI
  • Tracking
  • Segmentation
  • Reid
  • Localization
  • Generation
  • Inpainting
  • Image enhancement
  • Pose Estimation
  • Face
  • Video Understanding
  • Depth Estimation
  • Prediction
  • NAS
  • PointCloud
  • Fashion
  • Medical
• Cross-Modal
• Reference
• Acknowledgement

• Recurrent Models of Visual Attention [2014 deepmind NIPS]
• Neural Machine Translation by Jointly Learning to Align and Translate [ICLR 2015]

• Efficient Transformers: A Survey [paper]
• A Survey on Visual Transformer [paper]
• Transformers in Vision: A Survey [paper]

• Sequence to Sequence Learning with Neural Networks [NIPS 2014] [paper] [code]
• End-To-End Memory Networks [NIPS 2015] [paper] [code]
• Attention is all you need [NIPS 2017] [paper] [code]
• Bidirectional Encoder Representations from Transformers: BERT [paper] [code] [pretrained-models]
• Reformer: The Efficient Transformer [ICLR2020] [paper] [code]
• Linformer: Self-Attention with Linear Complexity [AAAI2020] [paper] [code]
• GPT-3: Language Models are Few-Shot Learners [NIPS 2020] [paper] [code]

• Dual-Path Transformer Network: Direct Context-Aware Modeling for End-to-End Monaural Speech Separation [INTERSPEECH 2020] [paper] [code]

• CoaT: Co-Scale Conv-Attentional Image Transformers [arxiv 2021] [paper] [code]
• SiT: Self-supervised vIsion Transformer [arxiv 2021] [paper] [code]
• VIT: An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale [VIT] [ICLR 2021] [paper] [code]
  • Trained with extra private data: do not generalized well when trained on insufficient amounts of data
• DeiT: Data-efficient Image Transformers [arxiv2021] [paper] [code]
  • Token-based strategy and build upon VIT and convolutional models
• Transformer in Transformer [arxiv 2021] [paper] [code1] [code-official]
• OmniNet: Omnidirectional Representations from Transformers [arxiv2021] [paper]
• Gaussian Context Transformer [CVPR 2021] [paper]
• General Multi-Label Image Classification With Transformers [CVPR 2021] [paper] [code]
• Scaling Local Self-Attention for Parameter Efficient Visual Backbones [CVPR 2021] [paper]
• T2T-ViT: Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet [ICCV 2021] [paper] [code]
• Swin Transformer: Hierarchical Vision Transformer using Shifted Windows [ICCV 2021] [paper] [code]
• Bias Loss for Mobile Neural Networks [ICCV 2021] [paper] [[code()]]
• Vision Transformer with Progressive Sampling [ICCV 2021] [paper] [[code(https://github.com/yuexy/PS-ViT)]]
• Rethinking Spatial Dimensions of Vision Transformers [ICCV 2021] [paper] [code]
• Rethinking and Improving Relative Position Encoding for Vision Transformer [ICCV 2021] [paper] [code]

• Convolutional Cifar10
• vision-transformers-cifar10
  • Found that performance was worse than simple resnet18
  • The influence of hyper-parameters: dim of vit, etc.
• ViT-pytorch
  • Using pretrained weights can get better results

• Emerging Properties in Self-Supervised Vision Transformers [ICCV 2021] [paper] [code]
• An Empirical Study of Training Self-Supervised Vision Transformers [ICCV 2021] [paper] [code]

• Transformer Interpretability Beyond Attention Visualization [CVPR 2021] [paper] [code]
• On the Adversarial Robustness of Visual Transformers [arxiv 2021] [paper]
• Robustness Verification for Transformers [ICLR 2020] [paper] [code]
• Pretrained Transformers Improve Out-of-Distribution Robustness [ACL 2020] [paper] [code]

• DETR: End-to-End Object Detection with Transformers [ECCV2020] [paper] [code]
• Deformable DETR: Deformable Transformers for End-to-End Object Detection [ICLR2021] [paper] [code]
• End-to-End Object Detection with Adaptive Clustering Transformer [arxiv2020] [paper]
• UP-DETR: Unsupervised Pre-training for Object Detection with Transformers [[arxiv2020] [paper]
• Rethinking Transformer-based Set Prediction for Object Detection [arxiv2020] [paper] [zhihu]
• End-to-end Lane Shape Prediction with Transformers [WACV 2021] [paper] [code]
• ViT-FRCNN: Toward Transformer-Based Object Detection [arxiv2020] [paper]
• Line Segment Detection Using Transformers [CVPR 2021] [paper] [code]
• Facial Action Unit Detection With Transformers [CVPR 2021] [paper] [code]
• Adaptive Image Transformer for One-Shot Object Detection [CVPR 2021] [paper] [code]
• Self-attention based Text Knowledge Mining for Text Detection [CVPR 2021] [paper] [code]
• Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions [ICCV 2021] [paper] [code]
• Group-Free 3D Object Detection via Transformers [ICCV 2021] [paper] [code]
• Fast Convergence of DETR with Spatially Modulated Co-Attention [ICCV 2021] [paper] [code]

• End-to-End Human Object Interaction Detection with HOI Transformer [CVPR 2021] [paper] [code]
• HOTR: End-to-End Human-Object Interaction Detection with Transformers [CVPR 2021] [paper] [code]

• Transformer Meets Tracker: Exploiting Temporal Context for Robust Visual Tracking [CVPR 2021] [paper] [code]
• TransTrack: Multiple-Object Tracking with Transformer [CVPR 2021] [paper] [code]
• Transformer Tracking [CVPR 2021] [paper] [code]
• Learning Spatio-Temporal Transformer for Visual Tracking [ICCV 2021] [paper] [code]

• SETR : Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers [CVPR 2021] [paper] [code]
• Trans2Seg: Transparent Object Segmentation with Transformer [arxiv2021] [paper] [code]
• End-to-End Video Instance Segmentation with Transformers [arxiv2020] [paper] [zhihu]
• MaX-DeepLab: End-to-End Panoptic Segmentation with Mask Transformers [CVPR 2021] [paper] [official-code] [unofficial-code]
• Medical Transformer: Gated Axial-Attention for Medical Image Segmentation [arxiv 2020] [paper] [code]
• SSTVOS: Sparse Spatiotemporal Transformers for Video Object Segmentation [CVPR 2021] [paper] [code]

• Diverse Part Discovery: Occluded Person Re-Identification With Part-Aware Transformer [CVPR 2021] [paper] [code]

• LoFTR: Detector-Free Local Feature Matching with Transformers [CVPR 2021] [paper] [code]
• MIST: Multiple Instance Spatial Transformer [CVPR 2021] [paper] [code]

• Variational Transformer Networks for Layout Generation [CVPR 2021] [paper] [code]
• TransGAN: Two Transformers Can Make One Strong GAN [paper] [code]
• Taming Transformers for High-Resolution Image Synthesis [CVPR 2021] [paper] [code]
• iGPT: Generative Pretraining from Pixels [ICML 2020] [paper] [code]
• Generative Adversarial Transformers [arxiv 2021] [paper] [code]
• LayoutTransformer: Scene Layout Generation With Conceptual and Spatial Diversity [CVPR2021] [paper[https://openaccess.thecvf.com/content/CVPR2021/html/Yang_LayoutTransformer_Scene_Layout_Generation_With_Conceptual_and_Spatial_Diversity_CVPR_2021_paper.html]] [code]
• Spatial-Temporal Transformer for Dynamic Scene Graph Generation [ICCV 2021] [paper]

• STTN: Learning Joint Spatial-Temporal Transformations for Video Inpainting [ECCV 2020] [paper] [code]

• Pre-Trained Image Processing Transformer [CVPR 2021] [paper]
• TTSR: Learning Texture Transformer Network for Image Super-Resolution [CVPR2020] [paper] [code]

• Pose Recognition with Cascade Transformers [CVPR 2021] [paper] [code]
• TransPose: Towards Explainable Human Pose Estimation by Transformer [arxiv 2020] [paper] [code]
• Hand-Transformer: Non-Autoregressive Structured Modeling for 3D Hand Pose Estimation [ECCV 2020] [paper]
• HOT-Net: Non-Autoregressive Transformer for 3D Hand-Object Pose Estimation [ACMMM 2020] [paper]
• End-to-End Human Pose and Mesh Reconstruction with Transformers [CVPR 2021] [paper] [code]
• 3D Human Pose Estimation with Spatial and Temporal Transformers [arxiv 2020] [paper] [code]
• End-to-End Trainable Multi-Instance Pose Estimation with Transformers [arxiv 2020] [paper]

• Robust Facial Expression Recognition with Convolutional Visual Transformers [arxiv 2020] [paper]
• Clusformer: A Transformer Based Clustering Approach to Unsupervised Large-Scale Face and Visual Landmark Recognition [CVPR 2021] [paper] [code]

• Is Space-Time Attention All You Need for Video Understanding? [arxiv 2020] [paper] [code]
• Temporal-Relational CrossTransformers for Few-Shot Action Recognition [CVPR 2021] [paper] [code]
• Self-Supervised Video Hashing via Bidirectional Transformers [CVPR 2021] [paper]
• SSAN: Separable Self-Attention Network for Video Representation Learning [CVPR 2021] [paper]

• Adabins：Depth Estimation using Adaptive Bins [CVPR 2021] [paper] [code]

• Multimodal Motion Prediction with Stacked Transformers [CVPR 2021] [paper] [code]
• Deep Transformer Models for Time Series Forecasting: The Influenza Prevalence Case [paper]
• Transformer networks for trajectory forecasting [ICPR 2020] [paper] [code]
• Spatial-Channel Transformer Network for Trajectory Prediction on the Traffic Scenes [arxiv 2021] [paper] [code]
• Pedestrian Trajectory Prediction using Context-Augmented Transformer Networks [ICRA 2020] [paper] [code]
• Spatio-Temporal Graph Transformer Networks for Pedestrian Trajectory Prediction [ECCV 2020] [paper] [code]
• Hierarchical Multi-Scale Gaussian Transformer for Stock Movement Prediction [paper]
• Single-Shot Motion Completion with Transformer [arxiv2021] [paper] [code]

• HR-NAS: Searching Efficient High-Resolution Neural Architectures with Transformers [CVPR 2021] [paper] [code]
• AutoFormer: Searching Transformers for Visual Recognition [ICCV 2021] [paper] [[code(https://github.com/microsoft/AutoML)]]

• Multi-Modal Fusion Transformer for End-to-End Autonomous Driving [CVPR 2021] [paper] [code]
• Point 4D Transformer Networks for Spatio-Temporal Modeling in Point Cloud Videos [CVPR 2021] [paper]

• Kaleido-BERT：Vision-Language Pre-training on Fashion Domain [CVPR 2021] [paper] [code]

• Lesion-Aware Transformers for Diabetic Retinopathy Grading [CVPR 2021] [paper]

• Thinking Fast and Slow: Efficient Text-to-Visual Retrieval with Transformers [CVPR 2021] [paper]
• Revamping Cross-Modal Recipe Retrieval with Hierarchical Transformers and Self-supervised Learning [CVPR2021] [paper] [code]
• Topological Planning With Transformers for Vision-and-Language Navigation [CVPR 2021] [paper]
• Multi-Stage Aggregated Transformer Network for Temporal Language Localization in Videos [CVPRR 2021] [paper]
• VLN BERT: A Recurrent Vision-and-Language BERT for Navigation [CVPR 2021] [paper] [code]
• Less Is More: ClipBERT for Video-and-Language Learning via Sparse Sampling [CVPR 2021] [paper] [code]

• Attention 机制详解1，2 zhihu1 zhihu2
• 自然语言处理中的自注意力机制（Self-attention Mechanism)
• Transformer模型原理详解 [zhihu] [csdn]
• 完全解析RNN, Seq2Seq, Attention注意力机制
• Seq2Seq and transformer implementation
• End-To-End Memory Networks [zhihu]
• Illustrating the key,query,value in attention
• Transformer in CV
• CVPR2021-Papers-with-Code
• ICCV2021-Papers-with-Code

Thanks for the awesome survey papers of Transformer.