{"list":"other","total":81,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1608.06993","title":"Densely Connected Convolutional Networks","created":"2016-08-25","cited_by_count":6720},{"id":"1905.11946","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","created":"2019-05-28","cited_by_count":6442},{"id":"1709.01507","title":"Squeeze-and-Excitation Networks","created":"2017-09-05","cited_by_count":4789},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"1409.4842","title":"Going Deeper with Convolutions","created":"2014-09-17","cited_by_count":4241},{"id":"1704.04861","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","created":"2017-04-17","cited_by_count":3845},{"id":"2004.05150","title":"Longformer: The Long-Document Transformer","created":"2020-04-10","cited_by_count":3413},{"id":"2105.15203","title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","created":"2021-05-31","cited_by_count":2940},{"id":"1807.06521","title":"CBAM: Convolutional Block Attention Module","created":"2018-07-17","cited_by_count":2477},{"id":"1610.02357","title":"Xception: Deep Learning with Depthwise Separable Convolutions","created":"2016-10-07","cited_by_count":2332},{"id":"2006.04768","title":"Linformer: Self-Attention with Linear Complexity","created":"2020-06-08","cited_by_count":1474},{"id":"2107.06278","title":"Per-Pixel Classification is Not All You Need for Semantic Segmentation","created":"2021-07-13","cited_by_count":1152},{"id":"1707.07012","title":"Learning Transferable Architectures for Scalable Image Recognition","created":"2017-07-21","cited_by_count":1101},{"id":"2101.11986","title":"Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet","created":"2021-01-28","cited_by_count":1101},{"id":"1406.2199","title":"Two-Stream Convolutional Networks for Action Recognition in Videos","created":"2014-06-09","cited_by_count":1068},{"id":"1602.07360","title":"SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size","created":"2016-02-24","cited_by_count":1060},{"id":"2101.01169","title":"Transformers in Vision: A Survey","created":"2021-01-04","cited_by_count":1013},{"id":"1809.02983","title":"Dual Attention Network for Scene Segmentation","created":"2018-09-09","cited_by_count":1003},{"id":"2106.04560","title":"Scaling Vision Transformers","created":"2021-06-08","cited_by_count":999},{"id":"2103.15808","title":"CvT: Introducing Convolutions to Vision Transformers","created":"2021-03-29","cited_by_count":947},{"id":"2105.05633","title":"Segmenter: Transformer for Semantic Segmentation","created":"2021-05-12","cited_by_count":855},{"id":"2103.14899","title":"CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification","created":"2021-03-27","cited_by_count":806},{"id":"1802.05751","title":"Image Transformer","created":"2018-02-15","cited_by_count":772},{"id":"2108.08810","title":"Do Vision Transformers See Like Convolutional Neural Networks?","created":"2021-08-19","cited_by_count":675},{"id":"2012.12556","title":"A Survey on Visual Transformer","created":"2020-12-23","cited_by_count":654},{"id":"2011.02523","title":"Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding","created":"2020-11-04","cited_by_count":604},{"id":"1910.03151","title":"ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks","created":"2019-10-08","cited_by_count":575},{"id":"2106.04803","title":"CoAtNet: Marrying Convolution and Attention for All Data Sizes","created":"2021-06-09","cited_by_count":569},{"id":"2101.02702","title":"TrackFormer: Multi-Object Tracking with Transformers","created":"2021-01-07","cited_by_count":518},{"id":"1712.00559","title":"Progressive Neural Architecture Search","created":"2017-12-02","cited_by_count":487},{"id":"2103.10697","title":"ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biases","created":"2021-03-19","cited_by_count":484},{"id":"1711.08565","title":"Person Transfer GAN to Bridge Domain Gap for Person Re-Identification","created":"2017-11-23","cited_by_count":480},{"id":"2104.01136","title":"LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference","created":"2021-04-02","cited_by_count":475},{"id":"2102.03902","title":"Nystr\\\"omformer: A Nystr\\\"om-Based Algorithm for Approximating Self-Attention","created":"2021-02-07","cited_by_count":471},{"id":"2106.04554","title":"A Survey of Transformers","created":"2021-06-08","cited_by_count":401},{"id":"2101.11605","title":"Bottleneck Transformers for Visual Recognition","created":"2021-01-27","cited_by_count":364},{"id":"1904.03582","title":"Multi-Label Image Recognition with Graph Convolutional Networks","created":"2019-04-07","cited_by_count":322},{"id":"2101.05224","title":"Big Self-Supervised Models Advance Medical Image Classification","created":"2021-01-13","cited_by_count":320},{"id":"2004.13621","title":"Exploring Self-attention for Image Recognition","created":"2020-04-28","cited_by_count":313},{"id":"2107.06263","title":"CMT: Convolutional Neural Networks Meet Vision Transformers","created":"2021-07-13","cited_by_count":310},{"id":"1911.09665","title":"Adversarial Examples Improve Image Recognition","created":"2019-11-21","cited_by_count":286},{"id":"1705.02953","title":"Temporal Segment Networks for Action Recognition in Videos","created":"2017-05-08","cited_by_count":279},{"id":"2206.01191","title":"EfficientFormer: Vision Transformers at MobileNet Speed","created":"2022-06-02","cited_by_count":241},{"id":"2108.05895","title":"Mobile-Former: Bridging MobileNet and Transformer","created":"2021-08-12","cited_by_count":235},{"id":"2006.06664","title":"Quasi-Dense Similarity Learning for Multiple Object Tracking","created":"2020-06-11","cited_by_count":220},{"id":"2106.03348","title":"ViTAE: Vision Transformer Advanced by Exploring Intrinsic Inductive Bias","created":"2021-06-07","cited_by_count":216},{"id":"1901.06032","title":"A Survey of the Recent Architectures of Deep Convolutional Neural Networks","created":"2019-01-17","cited_by_count":213},{"id":"2012.09165","title":"Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contexts","created":"2020-12-16","cited_by_count":210},{"id":"2107.14222","title":"Rethinking and Improving Relative Position Encoding for Vision Transformer","created":"2021-07-29","cited_by_count":207},{"id":"1912.07515","title":"Learning a Neural Solver for Multiple Object Tracking","created":"2019-12-16","cited_by_count":198},{"id":"2105.03889","title":"Conformer: Local Features Coupling Global Representations for Visual Recognition","created":"2021-05-09","cited_by_count":164},{"id":"1703.03872","title":"Deep Image Matting","created":"2017-03-10","cited_by_count":150},{"id":"2203.15102","title":"Rethinking Semantic Segmentation: A Prototype View","created":"2022-03-28","cited_by_count":140},{"id":"1906.11172","title":"Learning Data Augmentation Strategies for Object Detection","created":"2019-06-26","cited_by_count":139},{"id":"2209.04881","title":"On The Computational Complexity of Self-Attention","created":"2022-09-11","cited_by_count":139},{"id":"2102.08602","title":"LambdaNetworks: Modeling Long-Range Interactions Without Attention","created":"2021-02-17","cited_by_count":107},{"id":"1903.08469","title":"In Defense of Pre-trained ImageNet Architectures for Real-time Semantic Segmentation of Road-driving Images","created":"2019-03-20","cited_by_count":100},{"id":"1904.02216","title":"DFANet: Deep Feature Aggregation for Real-Time Semantic Segmentation","created":"2019-04-03","cited_by_count":100},{"id":"1805.08315","title":"Learning long-range spatial dependencies with horizontal gated-recurrent units","created":"2018-05-21","cited_by_count":98},{"id":"1808.08127","title":"Recalibrating Fully Convolutional Networks with Spatial and Channel 'Squeeze & Excitation' Blocks","created":"2018-08-23","cited_by_count":76},{"id":"2209.11345","title":"Swin2SR: SwinV2 Transformer for Compressed Image Super-Resolution and Restoration","created":"2022-09-22","cited_by_count":73},{"id":"2209.15001","title":"Dilated Neighborhood Attention Transformer","created":"2022-09-29","cited_by_count":64},{"id":"2301.03505","title":"Advances in Medical Image Analysis with Vision Transformers: A Comprehensive Review","created":"2023-01-09","cited_by_count":62},{"id":"1909.03402","title":"Squeeze-and-Attention Networks for Semantic Segmentation","created":"2019-09-08","cited_by_count":61},{"id":"2305.15272","title":"ViTMatte: Boosting Image Matting with Pretrained Plain Vision Transformers","created":"2023-05-24","cited_by_count":56},{"id":"1710.10741","title":"Evolving Deep Convolutional Neural Networks for Image Classification","created":"2017-10-30","cited_by_count":55},{"id":"2101.00590","title":"RegNet: Self-Regulated Network for Image Classification","created":"2021-01-03","cited_by_count":44},{"id":"2203.14509","title":"Automated Progressive Learning for Efficient Training of Vision Transformers","created":"2022-03-28","cited_by_count":37},{"id":"2305.09880","title":"A survey of the Vision Transformers and their CNN-Transformer based Variants","created":"2023-05-17","cited_by_count":33},{"id":"2206.00389","title":"A comparative study between vision transformers and CNNs in digital pathology","created":"2022-06-01","cited_by_count":16},{"id":"2208.03514","title":"Semiconductor Defect Detection by Hybrid Classical-Quantum Deep Learning","created":"2022-08-06","cited_by_count":16},{"id":"2207.13317","title":"Convolutional Embedding Makes Hierarchical Vision Transformer Stronger","created":"2022-07-27","cited_by_count":10},{"id":"2311.02803","title":"Fast and Interpretable Face Identification for Out-Of-Distribution Data Using Vision Transformers","created":"2023-11-06","cited_by_count":4},{"id":"2311.02747","title":"Attention Modules Improve Image-Level Anomaly Detection for Industrial Inspection: A DifferNet Case Study","created":"2023-11-05","cited_by_count":3}],"next_cursor":null}