Awesome-Visual-Transformer

(NIPS 2017)

[English Blog] Transformers in Vision [ ]

[Chinese Blog] 3W字长文带你轻松入门视觉transformer [ ]

[Chinese Blog] Vision Transformer 超详细解读 (原理分析+代码解读) [ ]

Multimodal learning with transformers: A survey (IEEE TPAMI) [ ] - 2023.05.11

A Survey of Visual Transformers [ ] - 2021.11.30

Transformers in Vision: A Survey [ ] - 2021.02.22

A Survey on Visual Transformer [ ] - 2021.1.30

A Survey of Transformers [ ] - 2020.6.09

Understanding Gaussian Attention Bias of Vision Transformers Using Effective Receptive [ ]

Focused Decoding Enables 3D Anatomical Detection by Transformers [ ] [ ]

TAG: Boosting Text-VQA via Text-aware Visual Question-answer Generation [ ] [ ]

Cross-Attention of Disentangled Modalities for 3D Human Mesh Recovery with Transformers [ ] [ ]

BatchFormer: Learning to Explore Sample Relationships for Robust Representation Learning [ ] [ ]

RelViT: Concept-guided Vision Transformer for Visual Relational Reasoning

Improved Multiscale Vision Transformers for Classification and Detection [ ] [ ]

DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection [ ] [ ]

Three things everyone should know about Vision Transformers [ ]

DeiT III: Revenge of the ViT [ ]

DaViT: Dual Attention Vision Transformers [ ] [ ]

Collaborative Transformers for Grounded Situation Recognition [ ] [ ]

Grounded Situation Recognition with Transformers [ ] [ ]

MaxViT: Multi-Axis Vision Transformer

V2X-ViT: Vehicle-to-Everything Cooperative Perception with Vision Transformer

Unsupervised Anomaly Detection in Medical Images with a Memory-augmented Multi-level Cross-attentional Masked Autoencoder [ ] [ ]

Contrastive Transformer-based Multiple Instance Learning for Weakly Supervised Polyp Frame Detection [ ] [ ]

VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training [ ] [ ]

PeCo: Perceptual Codebook for BERT Pre-training of Vision Transformers [ ]

ResViT: Residual vision transformers for multi-modal medical image synthesis [ ]

Combining EfficientNet and Vision Transformers for Video Deepfake Detection [ ] [ ]

Discrete Representations Strengthen Vision Transformer Robustness [ ]

StyleSwin: Transformer-based GAN for High-resolution Image Generation [ ] [ ]

Sliced Recursive Transformer [ ] [ ]

Dynamic Token Normalization Improves Vision Transformer [ ]

TokenLearner: What Can 8 Learned Tokens Do for Images and Videos? [ ] [ ]

Improved Robustness of Vision Transformer via PreLayerNorm in Patch Embedding [ ]

Object-Region Video Transformers [ ] [ ]

Adaptively Multi-view and Temporal Fusing Transformer for 3D Human Pose Estimation [ ] [ ]

NViT: Vision Transformer Compression and Parameter Redistribution [ ]

6D-ViT: Category-Level 6D Object Pose Estimation via Transformer-based Instance Representation Learning [ ]

Adversarial Token Attacks on Vision Transformers [ ]

Contextual Transformer Networks for Visual Recognition [ ] [ ]

TranSalNet: Visual saliency prediction using transformers [ ]

MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer [ ]

A free lunch from ViT: Adaptive Attention Multi-scale Fusion Transformer for Fine-grained Visual Recognition [ ]

3D-Transformer: Molecular Representation with Transformer in 3D Space [ ]

CCTrans: Simplifying and Improving Crowd Counting with Transformer [ ]

UFO-ViT: High Performance Linear Vision Transformer without Softmax [ ]

Sparse Spatial Transformers for Few-Shot Learning [ ]

Vision Transformer Hashing for Image Retrieval [ ]

OH-Former: Omni-Relational High-Order Transformer for Person Re-Identification [ ]

Pix2seq: A Language Modeling Framework for Object Detection [ ]

CoAtNet: Marrying Convolution and Attention for All Data Sizes [ ]

LOTR: Face Landmark Localization Using Localization Transformer [ ]

Transformer-Unet: Raw Image Processing with Unet [ ]

GraFormer: Graph Convolution Transformer for 3D Pose Estimation [ ]

CDTrans: Cross-domain Transformer for Unsupervised Domain Adaptation [ ]

PQ-Transformer: Jointly Parsing 3D Objects and Layouts from Point Clouds [ ] [ ]

Anchor DETR: Query Design for Transformer-Based Detector [ ] [ ]

DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETR [ ] [ ]

Efficient Transformer for Single Image Super-Resolution [ ]

MaskFormer: Per-Pixel Classification is Not All You Need for Semantic Segmentation [ ] [ ]

SwinIR: Image Restoration Using Swin Transformer [ ] [ ]

Trans4Trans: Efficient Transformer for Transparent Object and Semantic Scene Segmentation in Real-World Navigation Assistance [ ]

Do Vision Transformers See Like Convolutional Neural Networks? [ ]

Boosting Salient Object Detection with Transformer-based Asymmetric Bilateral U-Net [ ]

Light Field Image Super-Resolution with Transformers [ ] [ ]

Focal Self-attention for Local-Global Interactions in Vision Transformers [ ] [ ]

Polyp-PVT: Polyp Segmentation with Pyramid Vision Transformers [ ] [ ]

Mobile-Former: Bridging MobileNet and Transformer [ ]

TriTransNet: RGB-D Salient Object Detection with a Triplet Transformer Embedding Network [ ]

PSViT: Better Vision Transformer via Token Pooling and Attention Sharing [ ]

Boosting Few-shot Semantic Segmentation with Transformers [ ] [ ]

Congested Crowd Instance Localization with Dilated Convolutional Swin Transformer [ ]

Evo-ViT: Slow-Fast Token Evolution for Dynamic Vision Transformer [ ]

Styleformer: Transformer based Generative Adversarial Networks with Style Vector [ ] [ ]

CMT: Convolutional Neural Networks Meet Vision Transformers [ ]

TransAttUnet: Multi-level Attention-guided U-Net with Transformer for Medical Image Segmentation [ ]

TransClaw U-Net: Claw U-Net with Transformers for Medical Image Segmentation [ ]

ViTGAN: Training GANs with Vision Transformers [ ]

What Makes for Hierarchical Vision Transformer? [ ]

Trans4Trans: Efficient Transformer for Transparent Object Segmentation to Help Visually Impaired People Navigate in the Real World [ ]

Feature Fusion Vision Transformer for Fine-Grained Visual Categorization [ ]

TransformerFusion: Monocular RGB Scene Reconstruction using Transformers [ ]

Escaping the Big Data Paradigm with Compact Transformers [ ]

How to train your ViT? Data, Augmentation,and Regularization in Vision Transformers [ ]

Beyond Self-attention: External Attention using Two Linear Layers for Visual Tasks [ ]

XCiT: Cross-Covariance Image Transformers [ ] [ ]

Shuffle Transformer: Rethinking Spatial Shuffle for Vision Transformer [ ] [ ]

Video Swin Transformer [ ] [ ]

VOLO: Vision Outlooker for Visual Recognition [ ] [ ]

Transformer Meets Convolution: A Bilateral Awareness Net-work for Semantic Segmentation of Very Fine Resolution Ur-ban Scene Images [ ]

End-to-end Temporal Action Detection with Transformer [ ] [ ]

How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers [ ]

Efficient Self-supervised Vision Transformers for Representation Learning [ ]

Space-time Mixing Attention for Video Transformer [ ]

Transformed CNNs: recasting pre-trained convolutional layers with self-attention [ ]

CAT: Cross Attention in Vision Transformer [ ]

Scaling Vision Transformers [ ]

DETReg: Unsupervised Pretraining with Region Priors for Object Detection [ ] [ ]

Chasing Sparsity in Vision Transformers:An End-to-End Exploration [ ]

MViT: Mask Vision Transformer for Facial Expression Recognition in the wild [ ]

Demystifying Local Vision Transformer: Sparse Connectivity, Weight Sharing, and Dynamic Weight [ ]

On Improving Adversarial Transferability of Vision Transformers [ ]

Fully Transformer Networks for Semantic ImageSegmentation [ ]

Visual Transformer for Task-aware Active Learning [ ] [ ]

Efficient Training of Visual Transformers with Small-Size Datasets [ ]

Reveal of Vision Transformers Robustness against Adversarial Attacks [ ]

Person Re-Identification with a Locally Aware Transformer [ ]

Refiner: Refining Self-attention for Vision Transformers [ ]

ViTAE: Vision Transformer Advanced by Exploring Intrinsic Inductive Bias [ ]

Video Instance Segmentation using Inter-Frame Communication Transformers [ ]

Transformer in Convolutional Neural Networks [ ] [ ]

Uformer: A General U-Shaped Transformer for Image Restoration [ ] [ ]

Patch Slimming for Efficient Vision Transformers [ ]

RegionViT: Regional-to-Local Attention for Vision Transformers [ ]

Associating Objects with Transformers for Video Object Segmentation [ ] [ ]

Few-Shot Segmentation via Cycle-Consistent Transformer [ ]

Glance-and-Gaze Vision Transformer [ ] [ ]

Unsupervised MRI Reconstruction via Zero-Shot Learned Adversarial Transformers [ ]

DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification [ ] [ ]

When Vision Transformers Outperform ResNets without Pretraining or Strong Data Augmentations [ ] [ ]

Unsupervised Out-of-Domain Detection via Pre-trained Transformers [ ]

TransMIL: Transformer based Correlated Multiple Instance Learning for Whole Slide Image Classication [ ]

TransVOS: Video Object Segmentation with Transformers [ ]

KVT: k-NN Attention for Boosting Vision Transformers [ ]

MSG-Transformer: Exchanging Local Spatial Information by Manipulating Messenger Tokens [ ] [ ]

SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers [ ] [ ]

SDNet: mutil-branch for single image deraining using swin [ ] [ ]

Not All Images are Worth 16x16 Words: Dynamic Vision Transformers with Adaptive Sequence Length [ ]

Gaze Estimation using Transformer [ ] [ ]

Transformer-Based Deep Image Matching for Generalizable Person Re-identification [ ]

Less is More: Pay Less Attention in Vision Transformers [ ]

FoveaTer: Foveated Transformer for Image Classification [ ]

Transformer-Based Source-Free Domain Adaptation [ ] [ ]

An Attention Free Transformer [ ]

PTNet: A High-Resolution Infant MRI Synthesizer Based on Transformer [ ]

ResT: An Efficient Transformer for Visual Recognition [ ] [ ]

CogView: Mastering Text-to-Image Generation via Transformers [ ]

Aggregating Nested Transformers [ ]

Temporal Action Proposal Generation with Transformers [ ]

Boosting Crowd Counting with Transformers [ ]

COTR: Convolution in Transformer Network for End to End Polyp Detection [ ]

End-to-End Video Object Detection with Spatial-Temporal Transformers [ ] [ ]

Intriguing Properties of Vision Transformers [ ] [ ]

Combining Transformer Generators with Convolutional Discriminators [ ]

Rethinking the Design Principles of Robust Vision Transformer [ ]

Vision Transformers are Robust Learners [ ] [ ]

Manipulation Detection in Satellite Images Using Vision Transformer [ ]

Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentation [ ] [ ]

Self-Supervised Learning with Swin Transformers [ ] [ ]

SCTN: Sparse Convolution-Transformer Network for Scene Flow Estimation [ ]

RelationTrack: Relation-aware Multiple Object Tracking with Decoupled Representation [ ]

Visual Grounding with Transformers [ ]

Visual Composite Set Detection Using Part-and-Sum Transformers [ ]

TrTr: Visual Tracking with Transformer [ ] [ ]

MOTR: End-to-End Multiple-Object Tracking with TRansformer [ ] [ ]

Attention for Image Registration (AiR): an unsupervised Transformer approach [ ]

TransHash: Transformer-based Hamming Hashing for Efficient Image Retrieval [ ]

ISTR: End-to-End Instance Segmentation with Transformers [ ] [ ]

CAT: Cross-Attention Transformer for One-Shot Object Detection [ ]

CoSformer: Detecting Co-Salient Object with Transformers [ ]

End-to-End Attention-based Image Captioning [ ]

Pyramid Medical Transformer for Medical Image Segmentation [ ]

HandsFormer: Keypoint Transformer for Monocular 3D Pose Estimation ofHands and Object in Interaction [ ]

GasHis-Transformer: A Multi-scale Visual Transformer Approach for Gastric Histopathology Image Classification [ ]

Emerging Properties in Self-Supervised Vision Transformers [ ]

Inpainting Transformer for Anomaly Detection [ ]

Twins: Revisiting Spatial Attention Design in Vision Transformers [ ] [ ]

Point Cloud Learning with Transformer [ ]

Medical Transformer: Universal Brain Encoder for 3D MRI Analysis [ ]

ConTNet: Why not use convolution and transformer at the same time? [ ] [ ]

Dual Transformer for Point Cloud Analysis [ ]

Improve Vision Transformers Training by Suppressing Over-smoothing [ ] [ ]

Transformer Meets DCFAM: A Novel Semantic Segmentation Scheme for Fine-Resolution Remote Sensing Images [ ]

M3DeTR: Multi-representation, Multi-scale, Mutual-relation 3D Object Detection with Transformers [ ] [ ]

Skeletor: Skeletal Transformers for Robust Body-Pose Estimation [ ]

Learning to Cluster Faces via Transformer [ ]

Multiscale Vision Transformers [ ] [ ]

VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text [ ]

So-ViT: Mind Visual Tokens for Vision Transformer [ ] [ ]

Token Labeling: Training a 85.5% Top-1 Accuracy Vision Transformer with 56M Parameters on ImageNet [ ] [ ]

TransRPPG: Remote Photoplethysmography Transformer for 3D Mask Face Presentation Attack Detection [ ]

VideoGPT: Video Generation using VQ-VAE and Transformers [ ]

M2TR: Multi-modal Multi-scale Transformers for Deepfake Detection [ ]

Transformer Transforms Salient Object Detection and Camouflaged Object Detection [ ]

TransCrowd: Weakly-Supervised Crowd Counting with Transformer [ ] [ ]

Visual Transformer Pruning [ ]

Self-supervised Video Retrieval Transformer Network [ ]

Vision Transformer using Low-level Chest X-ray Feature Corpus for COVID-19 Diagnosis and Severity Quantification [ ]

TransGAN: Two Transformers Can Make One Strong GAN [ ] [ ]

Geometry-Free View Synthesis: Transformers and no 3D Priors [ ] [ ]

Co-Scale Conv-Attentional Image Transformers [ ] [ ]

LocalViT: Bringing Locality to Vision Transformers [ ] [ ]

Cloth Interactive Transformer for Virtual Try-On [ ] [ ]

Handwriting Transformers [ ]

SiT: Self-supervised vIsion Transformer [ ] [ ]

On the Robustness of Vision Transformers to Adversarial Examples [ ]

An Empirical Study of Training Self-Supervised Visual Transformers [ ]

A Video Is Worth Three Views: Trigeminal Transformers for Video-based Person Re-identification [ ]

Aggregated Contextual Transformations for High-Resolution Image Inpainting [ ] [ ]

Deepfake Detection Scheme Based on Vision Transformer and Distillation [ ]

Augmented Transformer with Adaptive Graph for Temporal Action Proposal Generation [ ]

TubeR: Tube-Transformer for Action Detection [ ]

AAformer: Auto-Aligned Transformer for Person Re-Identification [ ]

TFill: Image Completion via a Transformer-Based Architecture [ ]

Group-Free 3D Object Detection via Transformers [ ] [ ]

Spatial-Temporal Graph Transformer for Multiple Object Tracking [ ]

Going deeper with Image Transformers[ ]

Meta-DETR: Few-Shot Object Detection via Unified Image-Level Meta-Learning [ [ ]

DA-DETR: Domain Adaptive Detection Transformer by Hybrid Attention [ ]

Robust Facial Expression Recognition with Convolutional Visual Transformers [ ]

Thinking Fast and Slow: Efficient Text-to-Visual Retrieval with Transformers [ ]

Spatiotemporal Transformer for Video-based Person Re-identification[ ]

TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation [ ] [ ]

CvT: Introducing Convolutions to Vision Transformers [ ] [ ]

TFPose: Direct Human Pose Estimation with Transformers [ ]

TransCenter: Transformers with Dense Queries for Multiple-Object Tracking [ ]

Face Transformer for Recognition [ ]

On the Adversarial Robustness of Visual Transformers [ ]

Understanding Robustness of Transformers for Image Classification [ ]

Lifting Transformer for 3D Human Pose Estimation in Video [ ]

Global Self-Attention Networks for Image Recognition[ ]

High-Fidelity Pluralistic Image Completion with Transformers [ ] [ ]

Vision Transformers for Dense Prediction [ ] [ ]

TransFG: A Transformer Architecture for Fine-grained Recognition? [ ]

Is Space-Time Attention All You Need for Video Understanding? [ ]

Multi-view 3D Reconstruction with Transformer [ ]

Can Vision Transformers Learn without Natural Images? [ ] [ ]

End-to-End Trainable Multi-Instance Pose Estimation with Transformers [ ]

Instance-level Image Retrieval using Reranking Transformers [ ] [ ]

BossNAS: Exploring Hybrid CNN-transformers with Block-wisely Self-supervised Neural Architecture Search [ ] [ ]

Incorporating Convolution Designs into Visual Transformers [ ]

DeepViT: Towards Deeper Vision Transformer [ ]

Enhancing Transformer for Video Understanding Using Gated Multi-Level Attention and Temporal Adversarial Training [ ]

3D Human Pose Estimation with Spatial and Temporal Transformers [ ] [ ]

SUNETR: Transformers for 3D Medical Image Segmentation [ ]

Scalable Visual Transformers with Hierarchical Pooling [ ]

ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biases [ ]

TransMed: Transformers Advance Multi-modal Medical Image Classification [ ]

U-Net Transformer: Self and Cross Attention for Medical Image Segmentation [ ]

SpecTr: Spectral Transformer for Hyperspectral Pathology Image Segmentation [ ] [ ]

TransBTS: Multimodal Brain Tumor Segmentation Using Transformer [ ] [ ]

SSTN: Self-Supervised Domain Adaptation Thermal Object Detection for Autonomous Driving [ ]

Transformer is All You Need: Multimodal Multitask Learning with a Unified Transformer [ ] [ ]

Do We Really Need Explicit Position Encodings for Vision Transformers? [ ] [ ]

Deepfake Video Detection Using Convolutional Vision Transformer[ ]

Training Vision Transformers for Image Retrieval[ ]

Video Transformer Network[ ]

Bottleneck Transformers for Visual Recognition [ ]

CPTR: Full Transformer Network for Image Captioning [ ]

Learn to Dance with AIST++: Music Conditioned 3D Dance Generation [ ] [ ]

Segmenting Transparent Object in the Wild with Transformer [ ] [ ]

Investigating the Vision Transformer Model for Image Retrieval Tasks [ ]

Trear: Transformer-based RGB-D Egocentric Action Recognition [ ]

VisualSparta: Sparse Transformer Fragment-level Matching for Large-scale Text-to-Image Search [ ]

TrackFormer: Multi-Object Tracking with Transformers [ ]

Transformer Guided Geometry Model for Flow-Based Unsupervised Visual Odometry [ ]

Transformer for Image Quality Assessment [ ] [ ]

TransTrack: Multiple-Object Tracking with Transformer [ ] [ ]

Training data-efficient image transformers & distillation through attention [ ] [ ]

3D Object Detection with Pointformer [ ]

Toward Transformer-Based Object Detection [ ]

Taming Transformers for High-Resolution Image Synthesis [ ] [ ]

SceneFormer: Indoor Scene Generation with Transformers [ ]

PCT: Point Cloud Transformer [ ]

DETR for Pedestrian Detection[ ]

Transformer Guided Geometry Model for Flow-Based Unsupervised Visual Odometry[ ]

General Multi-label Image Classification with Transformers [ ]

P2T: Pyramid Pooling Transformer for Scene Understanding [ ]

Expanding Language-Image Pretrained Models for General Video Recognition [ ] [ ]

TinyViT: Fast Pretraining Distillation for Small Vision Transformers [ ] [ ]

Cross-Attention of Disentangled Modalities for 3D Human Mesh Recovery with Transformers [ ] [ ]

AiATrack: Attention in Attention for Transformer Visual Tracking [ ] [ ]

Joint Feature Learning and Relation Modeling for Tracking: A One-Stream Framework [ ] [ ]

Towards Grand Unification of Object Tracking [ ] [ ]

Tracking Objects as Pixel-wise Distributions [ ] [ ]

Masked Autoencoders Are Scalable Vision Learners [ ]

CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windows [ ] [ ]

Fast Point Transformer [ ]

EDTER: Edge Detection With Transformer [ ] [ ]

Bridged Transformer for Vision and Point Cloud 3D Object Detection [ ]

MNSRNet: Multimodal Transformer Network for 3D Surface Super-Resolution [ ]

HyperTransformer: A Textural and Spectral Feature Fusion Transformer for Pansharpening [ ] [ ]

Keypoint Transformer: Solving Joint Identification in Challenging Hands and Object Interactions for Accurate 3D Pose Estimation [ ]

MPViT: Multi-Path Vision Transformer for Dense Prediction [ ]

A-ViT: Adaptive Tokens for Efficient Vision Transformer [ ]

TopFormer: Token Pyramid Transformer for Mobile Semantic Segmentation [ ] [ ]

Continual Learning With Lifelong Vision Transformer [ ]

Swin Transformer V2: Scaling Up Capacity and Resolution [ ]

Voxel Set Transformer: A Set-to-Set Approach to 3D Object Detection From Point Clouds [ ] [ ]

Multi-Class Token Transformer for Weakly Supervised Semantic Segmentation [ ]

Human-Object Interaction Detection via Disentangled Transformer [ ]

LGT-Net: Indoor Panoramic Room Layout Estimation With Geometry-Aware Transformer Network [ ]

Sparse Local Patch Transformer for Robust Face Alignment and Landmarks Inherent Relation Learning [ ]

Vision Transformer With Deformable Attention [ ]

DearKD: Data-Efficient Early Knowledge Distillation for Vision Transformers [ ]

Restormer: Efficient Transformer for High-Resolution Image Restoration [ ] [ ]

Accelerating DETR Convergence via Semantic-Aligned Matching [ ] [ ]

BEVT: BERT Pretraining of Video Transformers [ ] [ ]

Mobile-Former: Bridging MobileNet and Transformer [ ]

Spatio-temporal Relation Modeling for Few-shot Action Recognition [ ] [ ]

MiniViT: Compressing Vision Transformers with Weight Multiplexing [ ] [ ]

Collaborative Transformers for Grounded Situation Recognition [ ] [ ]

Beyond Fixation: Dynamic Window Visual Transformer [ ] [ ]

Multimodal Token Fusion for Vision Transformers [ ]

Convolutional Neural Networks Meet Vision Transformers [ ]

Fine-tuning Image Transformers using Learnable Memory [ ]

Attend to Mix for Vision Transformers [ ] [ ]

Nominate Synergistic Context in Vision Transformer for Visual Recognition [ ] [ ]

Shunted Self-Attention via Multi-Scale Token Aggregation [ ] [ ]

Towards Robust Vision Transformer [ [ ]

Lite Vision Transformer with Enhanced Self-Attention [ [ ]

StyTr2: Image Style Transfer with Transformers [ ] [ ]

Image-Adaptive Hint Generation via Vision Transformer for Outpainting [ ] [ ]

ProTo: Program-Guided Transformer for Program-Guided Tasks [ ] [ ]

Augmented Shortcuts for Vision Transformers [ ] [ ]

You Only Look at One Sequence: Rethinking Transformer in Vision through Object Detection [ ] [ ]

Semantic Correspondence with Transformers [ ] [ ]

QVHighlights: Detecting Moments and Highlights in Videos via Natural Language Queries [ ] [ ]

Dual-stream Network for Visual Recognition [ ] [ ]

Container: Context Aggregation Network [ ] [ ]

Transformer in Transformer [ ] [ ]

T6D-Direct: Transformers for Multi-Object 6D Pose Direct Regression [ ]

Long Short-Term Transformer for Online Action Detection [ ]

TransformerFusion: Monocular RGB Scene Reconstruction using Transformers [ ]

TransMatcher: Deep Image Matching Through Transformers for Generalizable Person Re-identification [ ]

TransMIL: Transformer based Correlated Multiple Instance Learning for Whole Slide Image Classification [ ]

Associating Objects with Transformers for Video Object Segmentation [ ]

Test-Time Personalization with a Transformer for Human Pose Estimation [ ]

Revitalizing CNN Attention via Transformers in Self-Supervised Visual Representation Learning [ ]

Dynamic Grained Encoder for Vision Transformers [ ]

HRFormer: High-Resolution Vision Transformer for Dense Predict [ ]

Searching the Search Space of Vision Transformer [ ]

Not All Images are Worth 16x16 Words: Dynamic Transformers for Efficient Image Recognition [ ]

SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers [ ]

Do Vision Transformers See Like Convolutional Neural Networks? [ ]

Keeping Your Eye on the Ball: Trajectory Attention in Video Transformers [ ]

Glance-and-Gaze Vision Transformer [ ]

MST: Masked Self-Supervised Transformer for Visual Representation [ ]

DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification [ ]

TransGAN: Two Pure Transformers Can Make One Strong GAN, and That Can Scale Up [ ]

Augmented Shortcuts for Vision Transformers [ ]

Improved Transformer for High-Resolution GANs [ ]

All Tokens Matter: Token Labeling for Training Better Vision Transformers [ ]

XCiT: Cross-Covariance Image Transformers [ ]

Efficient Training of Visual Transformers with Small Datasets [ ]

Swin Transformer: Hierarchical Vision Transformer using Shifted Windows ( ) [ ] [ ]

High-Fidelity Pluralistic Image Completion with Transformers [ ] [ ]

PoinTr: Diverse Point Cloud Completion with Geometry-Aware Transformers ( ) [ ] [ ]

Revisiting Stereo Depth Estimation From a Sequence-to-Sequence Perspective with Transformers [ ] [ ]

Rethinking Transformer-based Set Prediction for Object Detection [ ]

Paint Transformer: Feed Forward Neural Painting with Stroke Prediction ( ) ) [ [ ]

3DVG-Transformer: Relation Modeling for Visual Grounding on Point Clouds [ ]

Training Vision Transformers from Scratch on ImageNet [ ] [ ]

THUNDR: Transformer-Based 3D Human Reconstruction With Markers [ ]

Multi-Scale Vision Longformer: A New Vision Transformer for High-Resolution Image Encoding [ ]

Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions [ ] [ ]

Spatial-Temporal Transformer for Dynamic Scene Graph Generation [ ]

GLiT: Neural Architecture Search for Global and Local Image Transformer [ ]

TRAR: Routing the Attention Spans in Transformer for Visual Question Answering [ ]

UniT: Multimodal Multitask Learning With a Unified Transformer [ ] [ ]

Stochastic Transformer Networks With Linear Competing Units: Application To End-to-End SL Translation [ ]

Transformer-Based Dual Relation Graph for Multi-Label Image Recognition [ ]

LocalTrans: A Multiscale Local Transformer Network for Cross-Resolution Homography Estimation [ ]

Improving 3D Object Detection With Channel-Wise Transformer [ ]

A Latent Transformer for Disentangled Face Editing in Images and Videos [ ] [ ]

GroupFormer: Group Activity Recognition With Clustered Spatial-Temporal Transformer [ ]

Unified Questioner Transformer for Descriptive Question Generation in Goal-Oriented Visual Dialogue [ ]

WB-DETR: Transformer-Based Detector Without Backbone [ ]

The Animation Transformer: Visual Correspondence via Segment Matching [ ]

The Animation Transformer: Visual Correspondence via Segment Matching [ ]

Relaxed Transformer Decoders for Direct Action Proposal Generation [ ]

Pyramid Point Cloud Transformer for Large-Scale Place Recognition [ ] [ ]

Multimodal Co-Attention Transformer for Survival Prediction in Gigapixel Whole Slide Images [ ]

Uncertainty-Guided Transformer Reasoning for Camouflaged Object Detection [ ]

Image Harmonization With Transformer [ ] [ ]

COTR: Correspondence Transformer for Matching Across Images [ ]

MUSIQ: Multi-Scale Image Quality Transformer [ ]

Episodic Transformer for Vision-and-Language Navigation [ ]

Action-Conditioned 3D Human Motion Synthesis With Transformer VAE [ ]

CrackFormer: Transformer Network for Fine-Grained Crack Detection [ ]

HiT: Hierarchical Transformer With Momentum Contrast for Video-Text Retrieval [ ]

Event-Based Video Reconstruction Using Transformer [ ]

STVGBert: A Visual-Linguistic Transformer Based Framework for Spatio-Temporal Video Grounding [ ]

HiFT: Hierarchical Feature Transformer for Aerial Tracking [ ] [ ]

DocFormer: End-to-End Transformer for Document Understanding [ ]

LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference [ ] [ ]

SignBERT: Pre-Training of Hand-Model-Aware Representation for Sign Language Recognition[ ]

VidTr: Video Transformer Without Convolutions [ ]

Action-Conditioned 3D Human Motion Synthesis with Transformer VAE [ ]

Segmenter: Transformer for Semantic Segmentation [ ] [ ]

Visformer: The Vision-friendly Transformer [ ] [ ]

PnP-DETR: Towards Efficient Visual Analysis with Transformers ( ) [ ] [ ]

[ ] Voxel Transformer for 3D Object Detection [ ]

TransVG: End-to-End Visual Grounding with Transformers [ ]

An End-to-End Transformer Model for 3D Object Detection [ ] [ ]

Eformer: Edge Enhancement based Transformer for Medical Image Denoising [ ]

TransFER: Learning Relation-aware Facial Expression Representations with Transformers [ ]

Oriented Object Detection with Transformer [ ]

ViViT: A Video Vision Transformer [ ]

Learning Spatio-Temporal Transformer for Visual Tracking [ ] [ ]

Improving 3D Object Detection with Channel-wise Transformer [ ]

Visual Saliency Transformer [ ]

Rethinking Spatial Dimensions of Vision Transformers [ ] [ ]

CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification [ ] [ ]

Point Transformer [ ]

TS-CAM: Token Semantic Coupled Attention Map for Weakly Supervised Object Localization [ ] [ ]

Visual Transformers: Token-based Image Representation and Processing for Computer Vision [ ]

Transformer-Based Attention Networks for Continuous Pixel-Wise Prediction [ ] [ ]

Conditional DETR for Fast Training Convergence [ ] [ ]

PIT: Position-Invariant Transform for Cross-FoV Domain Adaptation [ ] [ ]

SOTR: Segmenting Objects with Transformers [ ] [ ]

SnowflakeNet: Point Cloud Completion by Snowflake Point Deconvolution with Skip-Transformer [ ] [ ]

TransPose: Keypoint Localization via Transformer [ ] [ ]

TransReID: Transformer-based Object Re-Identification [ ] [ ]

Simpler is Better: Few-shot Semantic Segmentation with Classifier Weight Transformer [ ] [ ]

Anticipative Video Transformer [ ] [ ]

Rethinking and Improving Relative Position Encoding for Vision Transformer [ ] [ ]

Vision Transformer with Progressive Sampling [ ] [ ]

Fast Convergence of DETR with Spatially Modulated Co-Attention [ ] [ ]

AutoFormer: Searching Transformers for Visual Recognition [ ] [ ]

Diverse Part Discovery: Occluded Person Re-identification with Part-Aware Transformer [ ]

HOTR: End-to-End Human-Object Interaction Detection with Transformers ( ) [ ]

End-to-End Human Pose and Mesh Reconstruction with Transformers [ ]

Line Segment Detection Using Transformers without Edges [ ]

Multi-Modal Fusion Transformer for End-to-End Autonomous Driving [ ] [ ]

Pose Recognition with Cascade Transformers [ ]

Seeing Out of tHe bOx: End-to-End Pre-training for Vision-Language Representation Learning [ ]

LoFTR: Detector-Free Local Feature Matching with Transformers [ ] [ ]

Thinking Fast and Slow: Efficient Text-to-Visual Retrieval with Transformers [ ]

Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers [ ] [ ]

Transformer Tracking [ ] [ ]

Transformer Meets Tracker: Exploiting Temporal Context for Robust Visual Tracking (** oral**) [ ]

End-to-End Video Instance Segmentation with Transformers [ ]

Transformer Interpretability Beyond Attention Visualization [ ] [ ]

Pre-Trained Image Processing Transformer [ ]

UP-DETR: Unsupervised Pre-training for Object Detection with Transformers [ ]

Perceptual Image Quality Assessment with Transformers ( ) [ ]

High-Resolution Complex Scene Synthesis with Transformers ( ) [ ]

Collaborative Transformers for Grounded Situation Recognition [ ] [ ]

Generative Video Transformer: Can Objects be the Words? [ ]

Generative Adversarial Transformers [ ] [ ]

NDT-Transformer: Large-Scale 3D Point Cloud Localisation using the Normal Distribution Transform Representation [ ]

VTNet: Visual Transformer Network for Object Goal Navigation [ ]

An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale [ ] [ ]

Deformable DETR: Deformable Transformers for End-to-End Object Detection [ ] [ ]

MODELING LONG-RANGE INTERACTIONS WITHOUT ATTENTION [ ] [ ]

Video Transformer for Deepfake Detection with Incremental Learning[ ]

HAT: Hierarchical Aggregation Transformers for Person Re-identification [ ]

Token Shift Transformer for Video Classification [ ] [ ]

DPT: Deformable Patch-based Transformer for Visual Recognition [ ] [ ]

UTNet: A Hybrid Transformer Architecture for Medical Image Segmentation [ ] [ ]

Medical Transformer: Gated Axial-Attention for Medical Image Segmentation [ ] [ ]

Multi-Compound Transformer for Accurate Biomedical Image Segmentation [ ] [ ]

Progressively Normalized Self-Attention Network for Video Polyp Segmentation [ ] [ ]

A Multi-Branch Hybrid Transformer Networkfor Corneal Endothelial Cell Segmentation [ ]

End-to-End Object Detection with Adaptive Clustering Transformer [ ]

Grounded Situation Recognition with Transformers [ ] [ ]

TransFusion: Cross-view Fusion with Transformer for 3D Human Pose Estimation [ ] [ ]

VT-ADL: A Vision Transformer Network for Image Anomaly Detection and Localization ( ) [ ]

DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queries [ ]

Medical Image Segmentation using Squeeze-and-Expansion Transformers [ ]

You Only Group Once: Efficient Point-Cloud Processing with Token Representation and Relation Inference Module ( ) [ ] [ ]

PTT: Point-Track-Transformer Module for 3D Single Object Tracking in Point Clouds [ ] [ ]

End-to-end Lane Shape Prediction with Transformers [ ] [ ]

Vision Transformer for Fast and Efficient Scene Text Recognition [ ]

End-to-End Object Detection with Transformers ( ) [ ] [ ]

[ ] Feature Pyramid Transformer ( ) [ ] [ ]

Awesome-Transformer-Attention

[ ]