{"total":363,"rows":[{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403,"area":null},{"id":"2201.03545","title":"A ConvNet for the 2020s","created":"2022-01-10","cited_by_count":3579,"area":null},{"id":"2108.10257","title":"SwinIR: Image Restoration Using Swin Transformer","created":"2021-08-23","cited_by_count":1887,"area":null},{"id":"2111.09883","title":"Swin Transformer V2: Scaling Up Capacity and Resolution","created":"2021-11-18","cited_by_count":1228,"area":null},{"id":"2110.02178","title":"MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer","created":"2021-10-05","cited_by_count":642,"area":null},{"id":"2204.01697","title":"MaxViT: Multi-Axis Vision Transformer","created":"2022-04-04","cited_by_count":476,"area":null},{"id":"2205.04437","title":"Activating More Pixels in Image Super-Resolution Transformer","created":"2022-05-09","cited_by_count":438,"area":null},{"id":"2204.07118","title":"DeiT III: Revenge of the ViT","created":"2022-04-14","cited_by_count":419,"area":null},{"id":"2202.07925","title":"ActionFormer: Localizing Moments of Actions with Transformers","created":"2022-02-16","cited_by_count":311,"area":null},{"id":"2202.06709","title":"How Do Vision Transformers Work?","created":"2022-02-14","cited_by_count":307,"area":null},{"id":"2201.00520","title":"Vision Transformer with Deformable Attention","created":"2022-01-03","cited_by_count":295,"area":null},{"id":"2209.15425","title":"Spikformer: When Spiking Neural Network Meets Transformer","created":"2022-09-29","cited_by_count":271,"area":null},{"id":"2204.03883","title":"Vision Transformers for Single Image Dehazing","created":"2022-04-08","cited_by_count":260,"area":null},{"id":"2203.06173","title":"Masked Visual Pre-training for Motor Control","created":"2022-03-11","cited_by_count":248,"area":null},{"id":"2210.03109","title":"Real-World Robot Learning with Masked Visual Pre-training","created":"2022-10-06","cited_by_count":245,"area":null},{"id":"2108.05895","title":"Mobile-Former: Bridging MobileNet and Transformer","created":"2021-08-12","cited_by_count":235,"area":null},{"id":"2207.10666","title":"TinyViT: Fast Pretraining Distillation for Small Vision Transformers","created":"2022-07-21","cited_by_count":234,"area":null},{"id":"2111.15668","title":"AdaViT: Adaptive Vision Transformers for Efficient Image Recognition","created":"2021-11-30","cited_by_count":228,"area":null},{"id":"2203.15270","title":"MAT: Mask-Aware Transformer for Large Hole Image Inpainting","created":"2022-03-29","cited_by_count":218,"area":null},{"id":"2201.09450","title":"UniFormer: Unifying Convolution and Self-attention for Visual Recognition","created":"2022-01-24","cited_by_count":206,"area":null},{"id":"2201.09792","title":"Patches Are All You Need?","created":"2022-01-24","cited_by_count":201,"area":null},{"id":"2208.06677","title":"Adan: Adaptive Nesterov Momentum Algorithm for Faster Optimizing Deep Models","created":"2022-08-13","cited_by_count":174,"area":null},{"id":"2305.07027","title":"EfficientViT: Memory Efficient Vision Transformer with Cascaded Group Attention","created":"2023-05-11","cited_by_count":172,"area":null},{"id":"2308.00442","title":"FLatten Transformer: Vision Transformer using Focused Linear Attention","created":"2023-08-01","cited_by_count":171,"area":null},{"id":"2303.14189","title":"FastViT: A Fast Hybrid Vision Transformer using Structural Reparameterization","created":"2023-03-24","cited_by_count":162,"area":null},{"id":"2203.11183","title":"Masked Discrimination for Self-Supervised Learning on Point Clouds","created":"2022-03-21","cited_by_count":155,"area":null},{"id":"2110.09408","title":"HRFormer: High-Resolution Transformer for Dense Prediction","created":"2021-10-18","cited_by_count":149,"area":null},{"id":"2207.06966","title":"Scene Text Recognition with Permuted Autoregressive Sequence Models","created":"2022-07-14","cited_by_count":149,"area":null},{"id":"2402.16788","title":"Why Transformers Need Adam: A Hessian Perspective","created":"2024-02-26","cited_by_count":124,"area":null},{"id":"2307.09283","title":"RepViT: Revisiting Mobile CNN From ViT Perspective","created":"2023-07-18","cited_by_count":123,"area":null},{"id":"2206.10589","title":"EdgeNeXt: Efficiently Amalgamated CNN-Transformer Architecture for Mobile Vision Applications","created":"2022-06-21","cited_by_count":121,"area":null},{"id":"2111.12082","title":"PhysFormer: Facial Video-based Physiological Measurement with Temporal Difference Transformer","created":"2021-11-23","cited_by_count":120,"area":null},{"id":"2203.14211","title":"DepthFormer: Exploiting Long-Range Correlation and Local Information for Accurate Monocular Depth Estimation","created":"2022-03-27","cited_by_count":118,"area":null},{"id":"2111.06091","title":"A Survey of Visual Transformers","created":"2021-11-11","cited_by_count":117,"area":null},{"id":"2205.03436","title":"EdgeViTs: Competing Light-weight CNNs on Mobile Devices with Vision Transformers","created":"2022-05-06","cited_by_count":116,"area":null},{"id":"2211.09552","title":"UniFormerV2: Spatiotemporal Learning by Arming Image ViTs with Video UniFormer","created":"2022-11-17","cited_by_count":116,"area":null},{"id":"2207.10866","title":"Cost Aggregation with 4D Convolutional Swin Transformer for Few-Shot Segmentation","created":"2022-07-22","cited_by_count":114,"area":null},{"id":"2107.04589","title":"ViTGAN: Training GANs with Vision Transformers","created":"2021-07-09","cited_by_count":110,"area":null},{"id":"2206.04040","title":"MobileOne: An Improved One millisecond Mobile Backbone","created":"2022-06-08","cited_by_count":109,"area":null},{"id":"2305.03045","title":"OctFormer: Octree-based Transformers for 3D Point Clouds","created":"2023-05-04","cited_by_count":109,"area":null},{"id":"2205.03892","title":"ConvMAE: Masked Convolution Meets Masked Autoencoders","created":"2022-05-08","cited_by_count":105,"area":null},{"id":"2207.14284","title":"HorNet: Efficient High-Order Spatial Interactions with Recursive Gated Convolutions","created":"2022-07-28","cited_by_count":103,"area":null},{"id":"2404.03663","title":"Spike-driven Transformer V2: Meta Spiking Neural Network Architecture Inspiring the Design of Next-generation Neuromorphic Chips","created":"2024-02-15","cited_by_count":103,"area":null},{"id":"2205.12956","title":"Inception Transformer","created":"2022-05-25","cited_by_count":99,"area":null},{"id":"2303.00440","title":"Extracting Motion and Appearance via Inter-Frame Attention for Efficient Video Frame Interpolation","created":"2023-03-01","cited_by_count":98,"area":null},{"id":"2201.09405","title":"Improving Chest X-Ray Report Generation by Leveraging Warm Starting","created":"2022-01-24","cited_by_count":95,"area":null},{"id":"2111.01236","title":"Multi-Scale High-Resolution Vision Transformer for Semantic Segmentation","created":"2021-11-01","cited_by_count":92,"area":null},{"id":"2203.09795","title":"Three things everyone should know about Vision Transformers","created":"2022-03-18","cited_by_count":90,"area":null},{"id":"2203.00867","title":"Incremental Transformer Structure Enhanced Image Inpainting with Masking Positional Encoding","created":"2022-03-02","cited_by_count":83,"area":null},{"id":"2303.01870","title":"Revisiting Adversarial Training for ImageNet: Architectures, Training and Generalization across Threat Models","created":"2023-03-03","cited_by_count":79,"area":null},{"id":"2203.14681","title":"ObjectFormer for Image Manipulation Detection and Localization","created":"2022-03-28","cited_by_count":78,"area":null},{"id":"2205.13213","title":"Fast Vision Transformers with HiLo Attention","created":"2022-05-26","cited_by_count":78,"area":null},{"id":"2210.17409","title":"Deep Model Reassembly","created":"2022-10-24","cited_by_count":78,"area":null},{"id":"2301.10222","title":"RangeViT: Towards Vision Transformers for 3D Semantic Segmentation in Autonomous Driving","created":"2023-01-24","cited_by_count":76,"area":null},{"id":"2112.01388","title":"Residual Pathway Priors for Soft Equivariance Constraints","created":"2021-12-02","cited_by_count":75,"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":"2310.02642","title":"GET: Group Event Transformer for Event-Based Vision","created":"2023-10-04","cited_by_count":73,"area":null},{"id":"2306.13465","title":"3DSAM-adapter: Holistic adaptation of SAM from 2D to 3D for promptable tumor segmentation","created":"2023-06-23","cited_by_count":70,"area":null},{"id":"2108.13341","title":"Hire-MLP: Vision MLP via Hierarchical Rearrangement","created":"2021-08-30","cited_by_count":66,"area":null},{"id":"2309.05239","title":"HAT: Hybrid Attention Transformer for Image Restoration","created":"2023-09-11","cited_by_count":66,"area":null},{"id":"2208.05114","title":"Ghost-free High Dynamic Range Imaging with Context-aware Transformer","created":"2022-08-10","cited_by_count":65,"area":null},{"id":"2112.10175","title":"On Efficient Transformer-Based Image Pre-training for Low-Level Vision","created":"2021-12-19","cited_by_count":64,"area":null},{"id":"2111.06707","title":"Transformer-based Image Compression","created":"2021-11-12","cited_by_count":62,"area":null},{"id":"2304.10244","title":"Omni Aggregation Networks for Lightweight Image Super-Resolution","created":"2023-04-20","cited_by_count":62,"area":null},{"id":"2307.11545","title":"Bridging Vision and Language Encoders: Parameter-Efficient Tuning for Referring Image Segmentation","created":"2023-07-21","cited_by_count":61,"area":null},{"id":"2211.03295","title":"MogaNet: Multi-order Gated Aggregation Network","created":"2022-11-07","cited_by_count":59,"area":null},{"id":"2208.00173","title":"A Survey on Masked Autoencoder for Self-supervised Learning in Vision and Beyond","created":"2022-07-30","cited_by_count":58,"area":null},{"id":"2305.15272","title":"ViTMatte: Boosting Image Matting with Pretrained Plain Vision Transformers","created":"2023-05-24","cited_by_count":56,"area":null},{"id":"2401.16456","title":"SHViT: Single-Head Vision Transformer with Memory Efficient Macro Design","created":"2024-01-29","cited_by_count":56,"area":null},{"id":"2202.06817","title":"CATs++: Boosting Cost Aggregation with Convolutions and Transformers","created":"2022-02-14","cited_by_count":53,"area":null},{"id":"2201.09376","title":"ReconFormer: Accelerated MRI Reconstruction Using Recurrent Transformer","created":"2022-01-23","cited_by_count":52,"area":null},{"id":"2203.08392","title":"Patch-Fool: Are Vision Transformers Always Robust Against Adversarial Perturbations?","created":"2022-03-16","cited_by_count":49,"area":null},{"id":"2302.03548","title":"PhysFormer++: Facial Video-based Physiological Measurement with SlowFast Temporal Difference Transformer","created":"2023-02-07","cited_by_count":48,"area":null},{"id":"2210.01820","title":"MOAT: Alternating Mobile Convolution and Attention Brings Strong Vision Models","created":"2022-10-04","cited_by_count":47,"area":null},{"id":"2303.15105","title":"Vision Transformer with Quadrangle Attention","created":"2023-03-27","cited_by_count":46,"area":null},{"id":"2308.16258","title":"Robust Principles: Architectural Design Principles for Adversarially Robust CNNs","created":"2023-08-30","cited_by_count":46,"area":null},{"id":"2209.15159","title":"MobileViTv3: Mobile-Friendly Vision Transformer with Simple and Effective Fusion of Local, Global and Input Features","created":"2022-09-30","cited_by_count":44,"area":null},{"id":"2203.02557","title":"UVCGAN: UNet Vision Transformer cycle-consistent GAN for unpaired image-to-image translation","created":"2022-03-04","cited_by_count":42,"area":null},{"id":"2207.05557","title":"LightViT: Towards Light-Weight Convolution-Free Vision Transformers","created":"2022-07-12","cited_by_count":40,"area":null},{"id":"2404.00722","title":"DRCT: Saving Image Super-resolution away from Information Bottleneck","created":"2024-03-31","cited_by_count":40,"area":null},{"id":"2111.10659","title":"Are Vision Transformers Robust to Patch Perturbations?","created":"2021-11-20","cited_by_count":39,"area":null},{"id":"2206.03452","title":"Can CNNs Be More Robust Than Transformers?","created":"2022-06-07","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":"2404.07236","title":"Lightweight Deep Learning for Resource-Constrained Environments: A Survey","created":"2024-04-08","cited_by_count":38,"area":null},{"id":"2207.10040","title":"Single Frame Atmospheric Turbulence Mitigation: A Benchmark Study and A New Physics-Inspired Transformer Model","created":"2022-07-20","cited_by_count":37,"area":null},{"id":"2302.01572","title":"Simple, Effective and General: A New Backbone for Cross-view Image Geo-localization","created":"2023-02-03","cited_by_count":37,"area":null},{"id":"2111.12084","title":"Self-Supervised Pre-Training for Transformer-Based Person Re-Identification","created":"2021-11-23","cited_by_count":36,"area":null},{"id":"2304.00287","title":"Vision Transformers with Mixed-Resolution Tokenization","created":"2023-04-01","cited_by_count":36,"area":null},{"id":"2308.11358","title":"How Much Temporal Long-Term Context is Needed for Action Segmentation?","created":"2023-08-22","cited_by_count":36,"area":null},{"id":"2302.01791","title":"DilateFormer: Multi-Scale Dilated Transformer for Visual Recognition","created":"2023-02-03","cited_by_count":34,"area":null},{"id":"2201.10737","title":"Class-Aware Adversarial Transformers for Medical Image Segmentation","created":"2022-01-26","cited_by_count":33,"area":null},{"id":"2204.02964","title":"Unleashing Vanilla Vision Transformer with Masked Image Modeling for Object Detection","created":"2022-04-06","cited_by_count":33,"area":null},{"id":"2212.04970","title":"Masked Lip-Sync Prediction by Audio-Visual Contextual Exploitation in Transformers","created":"2022-12-09","cited_by_count":33,"area":null},{"id":"2207.12661","title":"Learning Visual Representation from Modality-Shared Contrastive Language-Image Pre-training","created":"2022-07-26","cited_by_count":32,"area":null},{"id":"2303.12621","title":"OcTr: Octree-based Transformer for 3D Object Detection","created":"2023-03-22","cited_by_count":32,"area":null},{"id":"2204.04667","title":"Linear Complexity Randomized Self-attention Mechanism","created":"2022-04-10","cited_by_count":31,"area":null},{"id":"2306.10898","title":"B-cos Alignment for Inherently Interpretable CNNs and Vision Transformers","created":"2023-06-19","cited_by_count":31,"area":null},{"id":"2401.02020","title":"Spikformer V2: Join the High Accuracy Club on ImageNet with an SNN Ticket","created":"2024-01-04","cited_by_count":30,"area":null},{"id":"2109.03810","title":"Scaled ReLU Matters for Training Vision Transformers","created":"2021-09-08","cited_by_count":29,"area":null},{"id":"2112.13692","title":"Augmenting Convolutional networks with attention-based aggregation","created":"2021-12-27","cited_by_count":29,"area":null}],"next_cursor":"100"}