{"total":2345,"rows":[{"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":"2102.02808","title":"Multi-Stage Progressive Image Restoration","created":"2021-02-04","cited_by_count":816,"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":"2301.00808","title":"ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders","created":"2023-01-02","cited_by_count":712,"area":null},{"id":"2106.00908","title":"TransMIL: Transformer based Correlated Multiple Instance Learning for Whole Slide Image Classification","created":"2021-06-02","cited_by_count":555,"area":null},{"id":"2204.08958","title":"MANIQA: Multi-dimension Attention Network for No-Reference Image Quality Assessment","created":"2022-04-19","cited_by_count":522,"area":null},{"id":"2204.01697","title":"MaxViT: Multi-Axis Vision Transformer","created":"2022-04-04","cited_by_count":476,"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":"2102.04906","title":"Dynamic Neural Networks: A Survey","created":"2021-02-09","cited_by_count":408,"area":null},{"id":"2107.06263","title":"CMT: Convolutional Neural Networks Meet Vision Transformers","created":"2021-07-13","cited_by_count":310,"area":null},{"id":"2201.02973","title":"MAXIM: Multi-Axis MLP for Image Processing","created":"2022-01-09","cited_by_count":302,"area":null},{"id":"2107.00641","title":"Focal Self-attention for Local-Global Interactions in Vision Transformers","created":"2021-07-01","cited_by_count":288,"area":null},{"id":"2103.12376","title":"Generalizing Face Forgery Detection with High-frequency Features","created":"2021-03-23","cited_by_count":262,"area":null},{"id":"2102.08005","title":"TransFuse: Fusing Transformers and CNNs for Medical Image Segmentation","created":"2021-02-16","cited_by_count":258,"area":null},{"id":"2103.11816","title":"Incorporating Convolution Designs into Visual Transformers","created":"2021-03-22","cited_by_count":248,"area":null},{"id":"2103.02907","title":"Coordinate Attention for Efficient Mobile Network Design","created":"2021-03-04","cited_by_count":241,"area":null},{"id":"2111.07624","title":"Attention Mechanisms in Computer Vision: A Survey","created":"2021-11-15","cited_by_count":232,"area":null},{"id":"2202.09741","title":"Visual Attention Network","created":"2022-02-20","cited_by_count":210,"area":null},{"id":"2106.05210","title":"Rethinking Space-Time Networks with Improved Memory Coverage for Efficient Video Object Segmentation","created":"2021-06-09","cited_by_count":203,"area":null},{"id":"2204.00987","title":"BinsFormer: Revisiting Adaptive Bins for Monocular Depth Estimation","created":"2022-04-03","cited_by_count":168,"area":null},{"id":"2106.13112","title":"VOLO: Vision Outlooker for Visual Recognition","created":"2021-06-24","cited_by_count":165,"area":null},{"id":"2105.03889","title":"Conformer: Local Features Coupling Global Representations for Visual Recognition","created":"2021-05-09","cited_by_count":164,"area":null},{"id":"2108.06932","title":"Polyp-PVT: Polyp Segmentation with Pyramid Vision Transformers","created":"2021-08-16","cited_by_count":159,"area":null},{"id":"2104.10475","title":"Camouflaged Object Segmentation with Distraction Mining","created":"2021-04-21","cited_by_count":151,"area":null},{"id":"2304.00501","title":"A Comprehensive Review of YOLO Architectures in Computer Vision: From YOLOv1 to YOLOv8 and YOLO-NAS","created":"2023-04-02","cited_by_count":151,"area":null},{"id":"2301.11514","title":"Deep Industrial Image Anomaly Detection: A Survey","created":"2023-01-27","cited_by_count":148,"area":null},{"id":"2307.01694","title":"Spike-driven Transformer","created":"2023-07-04","cited_by_count":146,"area":null},{"id":"2106.00487","title":"Dense Nested Attention Network for Infrared Small Target Detection","created":"2021-06-01","cited_by_count":135,"area":null},{"id":"2101.07663","title":"Salient Object Detection via Integrity Learning","created":"2021-01-19","cited_by_count":133,"area":null},{"id":"2103.10596","title":"PSCC-Net: Progressive Spatio-Channel Correlation Network for Image Manipulation Detection and Localization","created":"2021-03-19","cited_by_count":133,"area":null},{"id":"2210.13452","title":"MetaFormer Baselines for Vision","created":"2022-10-24","cited_by_count":132,"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":"2212.00968","title":"UIU-Net: U-Net in U-Net for Infrared Small Object Detection","created":"2022-12-02","cited_by_count":127,"area":null},{"id":"2308.03364","title":"Dual Aggregation Transformer for Image Super-Resolution","created":"2023-08-07","cited_by_count":124,"area":null},{"id":"2303.01904","title":"EcoTTA: Memory-Efficient Continual Test-time Adaptation via Self-distilled Regularization","created":"2023-03-03","cited_by_count":123,"area":null},{"id":"2307.09283","title":"RepViT: Revisiting Mobile CNN From ViT Perspective","created":"2023-07-18","cited_by_count":123,"area":null},{"id":"2207.14096","title":"Towards Large-Scale Small Object Detection: Survey and Benchmarks","created":"2022-07-28","cited_by_count":122,"area":null},{"id":"2103.10689","title":"Interpretable Deep Learning: Interpretation, Interpretability, Trustworthiness, and Beyond","created":"2021-03-19","cited_by_count":118,"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":"2107.00781","title":"UTNet: A Hybrid Transformer Architecture for Medical Image Segmentation","created":"2021-07-02","cited_by_count":116,"area":null},{"id":"2212.04497","title":"UNETR++: Delving into Efficient and Accurate 3D Medical Image Segmentation","created":"2022-12-08","cited_by_count":112,"area":null},{"id":"2206.14718","title":"LViT: Language meets Vision Transformer in Medical Image Segmentation","created":"2022-06-29","cited_by_count":111,"area":null},{"id":"2403.14614","title":"AdaIR: Adaptive All-in-One Image Restoration via Frequency Mining and Modulation","created":"2024-03-21","cited_by_count":111,"area":null},{"id":"2112.15089","title":"Causal Attention for Interpretable and Generalizable Graph Classification","created":"2021-12-30","cited_by_count":108,"area":null},{"id":"2102.08602","title":"LambdaNetworks: Modeling Long-Range Interactions Without Attention","created":"2021-02-17","cited_by_count":107,"area":null},{"id":"2209.13929","title":"Attention Spiking Neural Networks","created":"2022-09-28","cited_by_count":107,"area":null},{"id":"2204.02825","title":"An Empirical Study of Remote Sensing Pretraining","created":"2022-04-06","cited_by_count":105,"area":null},{"id":"2105.13381","title":"Recent advances and clinical applications of deep learning in medical image analysis","created":"2021-05-27","cited_by_count":104,"area":null},{"id":"2209.05588","title":"CenterFormer: Center-based Transformer for 3D Object Detection","created":"2022-09-12","cited_by_count":99,"area":null},{"id":"2403.00486","title":"Selective-Stereo: Adaptive Frequency Information Selection for Stereo Matching","created":"2024-03-01","cited_by_count":99,"area":null},{"id":"2303.09030","title":"Large Selective Kernel Network for Remote Sensing Object Detection","created":"2023-03-16","cited_by_count":98,"area":null},{"id":"2202.10304","title":"Real-Time Scene Text Detection with Differentiable Binarization and Adaptive Scale Fusion","created":"2022-02-21","cited_by_count":94,"area":null},{"id":"2304.13030","title":"CompletionFormer: Depth Completion with Convolutions and Vision Transformers","created":"2023-04-25","cited_by_count":93,"area":null},{"id":"2104.06403","title":"Lite-HRNet: A Lightweight High-Resolution Network","created":"2021-04-13","cited_by_count":91,"area":null},{"id":"2301.04805","title":"DEA-Net: Single image dehazing based on detail-enhanced convolution and content-guided attention","created":"2023-01-12","cited_by_count":91,"area":null},{"id":"2112.03590","title":"Contrastive Learning from Extremely Augmented Skeleton Sequences for Self-supervised Action Recognition","created":"2021-12-07","cited_by_count":90,"area":null},{"id":"2106.15125","title":"Constructing Stronger and Faster Baselines for Skeleton-based Action Recognition","created":"2021-06-29","cited_by_count":87,"area":null},{"id":"2301.06262","title":"Collaborative Perception in Autonomous Driving: Methods, Datasets and Challenges","created":"2023-01-16","cited_by_count":87,"area":null},{"id":"2208.10741","title":"Hierarchically Decomposed Graph Convolutional Networks for Skeleton-Based Action Recognition","created":"2022-08-23","cited_by_count":85,"area":null},{"id":"2310.00093","title":"DataDAM: Efficient Dataset Distillation with Attention Matching","created":"2023-09-29","cited_by_count":84,"area":null},{"id":"2108.11539","title":"TPH-YOLOv5: Improved YOLOv5 Based on Transformer Prediction Head for Object Detection on Drone-captured Scenarios","created":"2021-08-26","cited_by_count":83,"area":null},{"id":"2211.11943","title":"Conv2Former: A Simple Transformer-Style ConvNet for Visual Recognition","created":"2022-11-22","cited_by_count":81,"area":null},{"id":"2108.08782","title":"Causal Attention for Unbiased Visual Recognition","created":"2021-08-19","cited_by_count":80,"area":null},{"id":"2407.15420","title":"Local All-Pair Correspondence for Point Tracking","created":"2024-07-22","cited_by_count":80,"area":null},{"id":"2204.04656","title":"Video K-Net: A Simple, Strong, and Unified Baseline for Video Segmentation","created":"2022-04-10","cited_by_count":79,"area":null},{"id":"2308.07504","title":"ICAFusion: Iterative Cross-Attention Guided Feature Fusion for Multispectral Object Detection","created":"2023-08-15","cited_by_count":76,"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":"2104.06689","title":"Learning Normal Dynamics in Videos with Meta Prototype Network","created":"2021-04-14","cited_by_count":71,"area":null},{"id":"2311.02072","title":"HIPTrack: Visual Tracking with Historical Prompts","created":"2023-11-03","cited_by_count":71,"area":null},{"id":"2302.02515","title":"Deep Learning for Time Series Classification and Extrinsic Regression: A Current Survey","created":"2023-02-06","cited_by_count":68,"area":null},{"id":"2110.09482","title":"Self-Supervised Monocular Depth Estimation with Internal Feature Fusion","created":"2021-10-18","cited_by_count":67,"area":null},{"id":"2202.02980","title":"3D Object Detection from Images for Autonomous Driving: A Survey","created":"2022-02-07","cited_by_count":66,"area":null},{"id":"2203.02149","title":"HDNet: High-resolution Dual-domain Learning for Spectral Compressive Imaging","created":"2022-03-04","cited_by_count":66,"area":null},{"id":"2204.10704","title":"SUES-200: A Multi-height Multi-scene Cross-view Image Benchmark Across Drone and Satellite","created":"2022-04-22","cited_by_count":64,"area":null},{"id":"2405.06880","title":"EMCAD: Efficient Multi-scale Convolutional Attention Decoding for Medical Image Segmentation","created":"2024-05-11","cited_by_count":64,"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":"2107.02368","title":"UACANet: Uncertainty Augmented Context Attention for Polyp Segmentation","created":"2021-07-06","cited_by_count":61,"area":null},{"id":"2112.04491","title":"Improving Image Restoration by Revisiting Global Information Aggregation","created":"2021-12-08","cited_by_count":61,"area":null},{"id":"2203.08534","title":"Capturing Humans in Motion: Temporal-Attentive 3D Human Pose and Shape Estimation from Monocular Video","created":"2022-03-16","cited_by_count":60,"area":null},{"id":"2205.04280","title":"TGANet: Text-guided attention for improved polyp segmentation","created":"2022-05-09","cited_by_count":59,"area":null},{"id":"2211.01784","title":"MALUNet: A Multi-Attention and Light-weight UNet for Skin Lesion Segmentation","created":"2022-11-03","cited_by_count":59,"area":null},{"id":"2211.03295","title":"MogaNet: Multi-order Gated Aggregation Network","created":"2022-11-07","cited_by_count":59,"area":null},{"id":"2112.04903","title":"PRA-Net: Point Relation-Aware Network for 3D Point Cloud Analysis","created":"2021-12-09","cited_by_count":58,"area":null},{"id":"2203.12178","title":"Unifying Motion Deblurring and Frame Interpolation with Events","created":"2022-03-23","cited_by_count":58,"area":null},{"id":"2303.03202","title":"Continuous Sign Language Recognition with Correlation Network","created":"2023-03-06","cited_by_count":56,"area":null},{"id":"2308.03166","title":"Strategic Preys Make Acute Predators: Enhancing Camouflaged Object Detectors by Generating Camouflaged Objects","created":"2023-08-06","cited_by_count":56,"area":null},{"id":"2108.04204","title":"Meta Gradient Adversarial Attack","created":"2021-08-09","cited_by_count":55,"area":null},{"id":"2109.07270","title":"Distract Your Attention: Multi-head Cross Attention Network for Facial Expression Recognition","created":"2021-09-15","cited_by_count":55,"area":null},{"id":"2209.07947","title":"Omni-Dimensional Dynamic Convolution","created":"2022-09-16","cited_by_count":55,"area":null},{"id":"2102.00240","title":"SA-Net: Shuffle Attention for Deep Convolutional Neural Networks","created":"2021-01-30","cited_by_count":54,"area":null},{"id":"2104.14107","title":"Decoupled Dynamic Filter Networks","created":"2021-04-29","cited_by_count":53,"area":null},{"id":"2304.06793","title":"Speck: A Smart event-based Vision Sensor with a low latency 327K Neuron Convolutional Neuronal Network Processing Pipeline","created":"2023-04-13","cited_by_count":52,"area":null},{"id":"2312.12222","title":"EarthVQA: Towards Queryable Earth via Relational Reasoning-Based Remote Sensing Visual Question Answering","created":"2023-12-19","cited_by_count":52,"area":null},{"id":"2404.00876","title":"MGMap: Mask-Guided Learning for Online Vectorized HD Map Construction","created":"2024-04-01","cited_by_count":52,"area":null},{"id":"2103.16775","title":"Attention, please! A survey of Neural Attention Models in Deep Learning","created":"2021-03-31","cited_by_count":51,"area":null},{"id":"2206.10843","title":"Learning Debiased Classifier with Biased Committee","created":"2022-06-22","cited_by_count":51,"area":null},{"id":"2103.05687","title":"Capturing Omni-Range Context for Omnidirectional Segmentation","created":"2021-03-09","cited_by_count":50,"area":null},{"id":"2307.08579","title":"Scale-Aware Modulation Meet Transformer","created":"2023-07-17","cited_by_count":49,"area":null}],"next_cursor":"100"}