{"total":303,"rows":[{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139,"area":null},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968,"area":null},{"id":"2102.12122","title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","created":"2021-02-24","cited_by_count":1962,"area":null},{"id":"2103.13413","title":"Vision Transformers for Dense Prediction","created":"2021-03-24","cited_by_count":1803,"area":null},{"id":"2102.05095","title":"Is Space-Time Attention All You Need for Video Understanding?","created":"2021-02-09","cited_by_count":1620,"area":null},{"id":"2104.02057","title":"An Empirical Study of Training Self-Supervised Vision Transformers","created":"2021-04-05","cited_by_count":1616,"area":null},{"id":"2103.03206","title":"Perceiver: General Perception with Iterative Attention","created":"2021-03-04","cited_by_count":1104,"area":null},{"id":"2101.11986","title":"Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet","created":"2021-01-28","cited_by_count":1101,"area":null},{"id":"2101.01169","title":"Transformers in Vision: A Survey","created":"2021-01-04","cited_by_count":1013,"area":null},{"id":"2104.11227","title":"Multiscale Vision Transformers","created":"2021-04-22","cited_by_count":897,"area":null},{"id":"2103.14899","title":"CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification","created":"2021-03-27","cited_by_count":806,"area":null},{"id":"2103.17239","title":"Going deeper with Image Transformers","created":"2021-03-31","cited_by_count":764,"area":null},{"id":"2104.01136","title":"LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference","created":"2021-04-02","cited_by_count":475,"area":null},{"id":"2104.11178","title":"VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text","created":"2021-04-22","cited_by_count":429,"area":null},{"id":"2106.14881","title":"Early Convolutions Help Transformers See Better","created":"2021-06-28","cited_by_count":396,"area":null},{"id":"2210.05666","title":"Point Transformer V2: Grouped Vector Attention and Partition-based Pooling","created":"2022-10-11","cited_by_count":388,"area":null},{"id":"2101.11605","title":"Bottleneck Transformers for Visual Recognition","created":"2021-01-27","cited_by_count":364,"area":null},{"id":"2105.03404","title":"ResMLP: Feedforward networks for image classification with data-efficient training","created":"2021-05-07","cited_by_count":339,"area":null},{"id":"2106.09681","title":"XCiT: Cross-Covariance Image Transformers","created":"2021-06-17","cited_by_count":338,"area":null},{"id":"2103.11886","title":"DeepViT: Towards Deeper Vision Transformer","created":"2021-03-22","cited_by_count":289,"area":null},{"id":"2103.14586","title":"Understanding Robustness of Transformers for Image Classification","created":"2021-03-26","cited_by_count":249,"area":null},{"id":"2103.11816","title":"Incorporating Convolution Designs into Visual Transformers","created":"2021-03-22","cited_by_count":248,"area":null},{"id":"2111.07624","title":"Attention Mechanisms in Computer Vision: A Survey","created":"2021-11-15","cited_by_count":232,"area":null},{"id":"2101.10030","title":"Weakly-supervised Video Anomaly Detection with Robust Temporal Feature Magnitude Learning","created":"2021-01-25","cited_by_count":230,"area":null},{"id":"2104.06399","title":"Co-Scale Conv-Attentional Image Transformers","created":"2021-04-13","cited_by_count":224,"area":null},{"id":"2103.12731","title":"Scaling Local Self-Attention for Parameter Efficient Visual Backbones","created":"2021-03-23","cited_by_count":220,"area":null},{"id":"2102.10772","title":"UniT: Multimodal Multitask Learning with a Unified Transformer","created":"2021-02-22","cited_by_count":195,"area":null},{"id":"2112.06375","title":"Embracing Single Stride 3D Object Detector with Sparse Transformer","created":"2021-12-13","cited_by_count":193,"area":null},{"id":"2107.00651","title":"AutoFormer: Searching Transformers for Visual Recognition","created":"2021-07-01","cited_by_count":188,"area":null},{"id":"2111.05464","title":"Are Transformers More Robust Than CNNs?","created":"2021-11-10","cited_by_count":187,"area":null},{"id":"2203.14508","title":"Stratified Transformer for 3D Point Cloud Segmentation","created":"2022-03-28","cited_by_count":167,"area":null},{"id":"2106.13112","title":"VOLO: Vision Outlooker for Visual Recognition","created":"2021-06-24","cited_by_count":165,"area":null},{"id":"2104.12533","title":"Visformer: The Vision-friendly Transformer","created":"2021-04-26","cited_by_count":137,"area":null},{"id":"2110.11945","title":"SOFT: Softmax-free Transformer with Linear Complexity","created":"2021-10-22","cited_by_count":128,"area":null},{"id":"2106.02689","title":"RegionViT: Regional-to-Local Attention for Vision Transformers","created":"2021-06-04","cited_by_count":127,"area":null},{"id":"2106.11297","title":"TokenLearner: What Can 8 Learned Tokens Do for Images and Videos?","created":"2021-06-21","cited_by_count":127,"area":null},{"id":"2103.05630","title":"ForgeryNet: A Versatile Benchmark for Comprehensive Forgery Analysis","created":"2021-03-09","cited_by_count":126,"area":null},{"id":"2303.12766","title":"Spherical Transformer for LiDAR-based 3D Recognition","created":"2023-03-22","cited_by_count":125,"area":null},{"id":"2304.09854","title":"Transformer-Based Visual Segmentation: A Survey","created":"2023-04-19","cited_by_count":124,"area":null},{"id":"2103.14862","title":"TS-CAM: Token Semantic Coupled Attention Map for Weakly Supervised Object Localization","created":"2021-03-27","cited_by_count":123,"area":null},{"id":"2103.01209","title":"Generative Adversarial Transformers","created":"2021-03-01","cited_by_count":120,"area":null},{"id":"2111.06091","title":"A Survey of Visual Transformers","created":"2021-11-11","cited_by_count":117,"area":null},{"id":"2203.16768","title":"ReSTR: Convolution-free Referring Image Segmentation Using Transformers","created":"2022-03-31","cited_by_count":112,"area":null},{"id":"2203.13250","title":"Global Tracking Transformers","created":"2022-03-24","cited_by_count":110,"area":null},{"id":"2105.02358","title":"Beyond Self-attention: External Attention using Two Linear Layers for Visual Tasks","created":"2021-05-05","cited_by_count":109,"area":null},{"id":"2102.08602","title":"LambdaNetworks: Modeling Long-Range Interactions Without Attention","created":"2021-02-17","cited_by_count":107,"area":null},{"id":"2101.08833","title":"SSTVOS: Sparse Spatiotemporal Transformers for Video Object Segmentation","created":"2021-01-21","cited_by_count":106,"area":null},{"id":"2104.10154","title":"Variational Relational Point Completion Network","created":"2021-04-20","cited_by_count":104,"area":null},{"id":"2112.04702","title":"Fast Point Transformer","created":"2021-12-09","cited_by_count":104,"area":null},{"id":"2207.05736","title":"Vision Transformer for NeRF-Based View Synthesis from a Single Input Image","created":"2022-07-12","cited_by_count":104,"area":null},{"id":"2103.06255","title":"Involution: Inverting the Inherence of Convolution for Visual Recognition","created":"2021-03-10","cited_by_count":99,"area":null},{"id":"2107.12292","title":"Contextual Transformer Networks for Visual Recognition","created":"2021-07-26","cited_by_count":90,"area":null},{"id":"2303.16900","title":"InceptionNeXt: When Inception Meets ConvNeXt","created":"2023-03-29","cited_by_count":86,"area":null},{"id":"2210.01427","title":"Accurate Image Restoration with Attention Retractable Transformer","created":"2022-10-04","cited_by_count":85,"area":null},{"id":"2204.05525","title":"TopFormer: Token Pyramid Transformer for Mobile Semantic Segmentation","created":"2022-04-12","cited_by_count":82,"area":null},{"id":"2207.04978","title":"Wave-ViT: Unifying Wavelet and Transformers for Visual Representation Learning","created":"2022-07-11","cited_by_count":78,"area":null},{"id":"2108.09666","title":"Relational Embedding for Few-Shot Classification","created":"2021-08-22","cited_by_count":74,"area":null},{"id":"2111.14556","title":"On the Integration of Self-Attention and Convolution","created":"2021-11-29","cited_by_count":74,"area":null},{"id":"2111.11187","title":"PointMixer: MLP-Mixer for Point Cloud Understanding","created":"2021-11-22","cited_by_count":71,"area":null},{"id":"2106.00515","title":"KVT: k-NN Attention for Boosting Vision Transformers","created":"2021-05-28","cited_by_count":65,"area":null},{"id":"2112.02857","title":"PTTR: Relational 3D Point Cloud Object Tracking with Transformer","created":"2021-12-06","cited_by_count":65,"area":null},{"id":"2111.04076","title":"Direct Multi-view Multi-person 3D Pose Estimation","created":"2021-11-07","cited_by_count":64,"area":null},{"id":"2112.10809","title":"Lite Vision Transformer with Enhanced Self-Attention","created":"2021-12-20","cited_by_count":64,"area":null},{"id":"2203.14263","title":"A General Survey on Attention Mechanisms in Deep Learning","created":"2022-03-27","cited_by_count":64,"area":null},{"id":"2103.12236","title":"Instance-level Image Retrieval using Reranking Transformers","created":"2021-03-22","cited_by_count":63,"area":null},{"id":"2106.04263","title":"On the Connection between Local Attention and Dynamic Depth-wise Convolution","created":"2021-06-08","cited_by_count":62,"area":null},{"id":"2108.06455","title":"PTT: Point-Track-Transformer Module for 3D Single Object Tracking in Point Clouds","created":"2021-08-14","cited_by_count":59,"area":null},{"id":"2102.07448","title":"OmniDet: Surround View Cameras based Multi-task Visual Perception Network for Autonomous Driving","created":"2021-02-15","cited_by_count":57,"area":null},{"id":"2107.02960","title":"GLiT: Neural Architecture Search for Global and Local Image Transformer","created":"2021-07-07","cited_by_count":53,"area":null},{"id":"2101.11604","title":"Shape or Texture: Understanding Discriminative Features in CNNs","created":"2021-01-27","cited_by_count":52,"area":null},{"id":"2302.04973","title":"Invariant Slot Attention: Object Discovery with Slot-Centric Reference Frames","created":"2023-02-09","cited_by_count":51,"area":null},{"id":"2105.01290","title":"Dual-Cross Central Difference Network for Face Anti-Spoofing","created":"2021-05-04","cited_by_count":47,"area":null},{"id":"2105.15168","title":"MSG-Transformer: Exchanging Local Spatial Information by Manipulating Messenger Tokens","created":"2021-05-31","cited_by_count":46,"area":null},{"id":"2108.06076","title":"PVT: Point-Voxel Transformer for Point Cloud Learning","created":"2021-08-13","cited_by_count":43,"area":null},{"id":"2204.02557","title":"MixFormer: Mixing Features across Windows and Dimensions","created":"2022-04-06","cited_by_count":43,"area":null},{"id":"2106.02277","title":"Glance-and-Gaze Vision Transformer","created":"2021-06-04","cited_by_count":42,"area":null},{"id":"2112.14889","title":"Few-shot Backdoor Defense Using Shapley Estimation","created":"2021-12-30","cited_by_count":41,"area":null},{"id":"2303.16450","title":"Self-positioning Point-based Transformer for Point Cloud Understanding","created":"2023-03-29","cited_by_count":40,"area":null},{"id":"2104.13497","title":"ConTNet: Why not use convolution and transformer at the same time?","created":"2021-04-27","cited_by_count":38,"area":null},{"id":"2304.04237","title":"Slide-Transformer: Hierarchical Vision Transformer with Local Self-Attention","created":"2023-04-09","cited_by_count":38,"area":null},{"id":"2206.14383","title":"Overview of Deep Learning-based CSI Feedback in Massive MIMO Systems","created":"2022-06-29","cited_by_count":37,"area":null},{"id":"2104.12928","title":"If your data distribution shifts, use self-learning","created":"2021-04-27","cited_by_count":36,"area":null},{"id":"2203.10790","title":"ScalableViT: Rethinking the Context-oriented Generalization of Vision Transformer","created":"2022-03-21","cited_by_count":36,"area":null},{"id":"2107.02133","title":"Test-Time Personalization with a Transformer for Human Pose Estimation","created":"2021-07-05","cited_by_count":33,"area":null},{"id":"2101.06635","title":"Context-aware Attentional Pooling (CAP) for Fine-grained Visual Classification","created":"2021-01-17","cited_by_count":31,"area":null},{"id":"2102.07092","title":"Learning Self-Similarity in Space and Time as Generalized Motion for Video Action Recognition","created":"2021-02-14","cited_by_count":31,"area":null},{"id":"2205.07417","title":"Transformers in 3D Point Clouds: A Survey","created":"2022-05-16","cited_by_count":31,"area":null},{"id":"2103.16748","title":"Dual Contrastive Loss and Attention for GANs","created":"2021-03-31","cited_by_count":30,"area":null},{"id":"2201.10801","title":"When Shift Operation Meets Vision Transformer: An Extremely Simple Alternative to Attention Mechanism","created":"2022-01-26","cited_by_count":30,"area":null},{"id":"2208.02879","title":"PointConvFormer: Revenge of the Point-based Convolution","created":"2022-08-04","cited_by_count":30,"area":null},{"id":"2108.12468","title":"Learning Inner-Group Relations on Point Clouds","created":"2021-08-27","cited_by_count":29,"area":null},{"id":"2207.04976","title":"Dual Vision Transformer","created":"2022-07-11","cited_by_count":29,"area":null},{"id":"2110.08192","title":"Attention meets Geometry: Geometry Guided Spatial-Temporal Attention for Consistent Self-Supervised Monocular Depth Estimation","created":"2021-10-15","cited_by_count":27,"area":null},{"id":"2112.11435","title":"Learned Queries for Efficient Local Attention","created":"2021-12-21","cited_by_count":27,"area":null},{"id":"2209.00860","title":"Real-time 3D Single Object Tracking with Transformer","created":"2022-09-02","cited_by_count":27,"area":null},{"id":"2210.05616","title":"Neural Shape Deformation Priors","created":"2022-10-11","cited_by_count":27,"area":null},{"id":"2306.06722","title":"$E(2)$-Equivariant Vision Transformer","created":"2023-06-11","cited_by_count":27,"area":null},{"id":"2104.04420","title":"SVDistNet: Self-Supervised Near-Field Distance Estimation on Surround View Fisheye Cameras","created":"2021-04-09","cited_by_count":25,"area":null},{"id":"2203.00828","title":"3DCTN: 3D Convolution-Transformer Network for Point Cloud Classification","created":"2022-03-02","cited_by_count":25,"area":null},{"id":"2105.04447","title":"SCTN: Sparse Convolution-Transformer Network for Scene Flow Estimation","created":"2021-05-10","cited_by_count":23,"area":null}],"next_cursor":"100"}