{"list":"other","total":66,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"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":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"id":"1612.03144","title":"Feature Pyramid Networks for Object Detection","created":"2016-12-09","cited_by_count":5036},{"id":"1411.4038","title":"Fully Convolutional Networks for Semantic Segmentation","created":"2014-11-14","cited_by_count":4859},{"id":"1709.01507","title":"Squeeze-and-Excitation Networks","created":"2017-09-05","cited_by_count":4789},{"id":"1804.02767","title":"YOLOv3: An Incremental Improvement","created":"2018-04-08","cited_by_count":2659},{"id":"1807.06521","title":"CBAM: Convolutional Block Attention Module","created":"2018-07-17","cited_by_count":2477},{"id":"2102.12122","title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","created":"2021-02-24","cited_by_count":1962},{"id":"1306.5151","title":"Fine-Grained Visual Classification of Aircraft","created":"2013-06-21","cited_by_count":1726},{"id":"2111.09883","title":"Swin Transformer V2: Scaling Up Capacity and Resolution","created":"2021-11-18","cited_by_count":1228},{"id":"1511.07122","title":"Multi-Scale Context Aggregation by Dilated Convolutions","created":"2015-11-23","cited_by_count":1133},{"id":"1906.02629","title":"When Does Label Smoothing Help?","created":"2019-06-06","cited_by_count":988},{"id":"2103.15808","title":"CvT: Introducing Convolutions to Vision Transformers","created":"2021-03-29","cited_by_count":947},{"id":"2104.11227","title":"Multiscale Vision Transformers","created":"2021-04-22","cited_by_count":897},{"id":"1406.4729","title":"Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition","created":"2014-06-18","cited_by_count":720},{"id":"1504.06375","title":"Holistically-Nested Edge Detection","created":"2015-04-24","cited_by_count":592},{"id":"1910.03151","title":"ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks","created":"2019-10-08","cited_by_count":575},{"id":"1412.7062","title":"Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs","created":"2014-12-22","cited_by_count":554},{"id":"2112.01526","title":"MViTv2: Improved Multiscale Vision Transformers for Classification and Detection","created":"2021-12-02","cited_by_count":519},{"id":"2204.01697","title":"MaxViT: Multi-Axis Vision Transformer","created":"2022-04-04","cited_by_count":476},{"id":"1904.01169","title":"Res2Net: A New Multi-scale Backbone Architecture","created":"2019-04-02","cited_by_count":470},{"id":"1906.03731","title":"Is Attention Interpretable?","created":"2019-06-09","cited_by_count":389},{"id":"1705.09914","title":"Dilated Residual Networks","created":"2017-05-28","cited_by_count":294},{"id":"1803.08904","title":"Context Encoding for Semantic Segmentation","created":"2018-03-23","cited_by_count":290},{"id":"2204.07143","title":"Neighborhood Attention Transformer","created":"2022-04-14","cited_by_count":239},{"id":"1906.06423","title":"Fixing the train-test resolution discrepancy","created":"2019-06-14","cited_by_count":209},{"id":"2109.04335","title":"UCTransNet: Rethinking the Skip Connections in U-Net from a Channel-wise Perspective with Transformer","created":"2021-09-09","cited_by_count":197},{"id":"2303.08810","title":"BiFormer: Vision Transformer with Bi-Level Routing Attention","created":"2023-03-15","cited_by_count":151},{"id":"1612.02103","title":"Richer Convolutional Features for Edge Detection","created":"2016-12-07","cited_by_count":143},{"id":"1810.12348","title":"Gather-Excite: Exploiting Feature Context in Convolutional Neural Networks","created":"2018-10-29","cited_by_count":139},{"id":"2103.07976","title":"TransFG: A Transformer Architecture for Fine-grained Recognition","created":"2021-03-14","cited_by_count":132},{"id":"1711.06897","title":"Single-Shot Refinement Neural Network for Object Detection","created":"2017-11-18","cited_by_count":129},{"id":"1407.3867","title":"Part-based R-CNNs for Fine-grained Category Detection","created":"2014-07-15","cited_by_count":109},{"id":"1809.00287","title":"Learning to Navigate for Fine-grained Classification","created":"2018-09-02","cited_by_count":103},{"id":"1903.06150","title":"Looking for the Devil in the Details: Learning Trilinear Attention Sampling Network for Fine-grained Image Recognition","created":"2019-03-14","cited_by_count":95},{"id":"2003.03836","title":"Fine-Grained Visual Classification via Progressive Multi-Granularity Training of Jigsaw Patches","created":"2020-03-08","cited_by_count":92},{"id":"2108.11116","title":"TransFER: Learning Relation-aware Facial Expression Representations with Transformers","created":"2021-08-25","cited_by_count":85},{"id":"2002.10191","title":"Learning Attentive Pairwise Interaction for Fine-Grained Classification","created":"2020-02-24","cited_by_count":84},{"id":"2205.02151","title":"Dual Cross-Attention Learning for Fine-Grained Visual Categorization and Object Re-Identification","created":"2022-05-04","cited_by_count":78},{"id":"1811.04533","title":"M2Det: A Single-Shot Object Detector based on Multi-Level Feature Pyramid Network","created":"2018-11-12","cited_by_count":76},{"id":"2005.10411","title":"Interpretable and Accurate Fine-grained Recognition via Region Grouping","created":"2020-05-21","cited_by_count":75},{"id":"1411.6447","title":"The Application of Two-level Attention Models in Deep Convolutional Neural Network for Fine-grained Image Classification","created":"2014-11-24","cited_by_count":67},{"id":"1903.02827","title":"Weakly Supervised Complementary Parts Models for Fine-Grained Image Classification from the Bottom Up","created":"2019-03-07","cited_by_count":66},{"id":"1809.05934","title":"Maximum-Entropy Fine-Grained Classification","created":"2018-09-16","cited_by_count":65},{"id":"2002.04264","title":"The Devil is in the Channels: Mutual-Channel Loss for Fine-Grained Image Classification","created":"2020-02-11","cited_by_count":64},{"id":"1512.08086","title":"Part-Stacked CNN for Fine-Grained Visual Categorization","created":"2015-12-26","cited_by_count":62},{"id":"1909.04412","title":"Cross-X Learning for Fine-Grained Visual Categorization","created":"2019-09-10","cited_by_count":61},{"id":"1704.01740","title":"Object-Part Attention Model for Fine-grained Image Classification","created":"2017-04-06","cited_by_count":54},{"id":"1911.03621","title":"Learning Deep Bilinear Transformation for Fine-grained Image Representation","created":"2019-11-09","cited_by_count":54},{"id":"1909.11378","title":"Attention Convolutional Binary Neural Tree for Fine-Grained Visual Categorization","created":"2019-09-25","cited_by_count":51},{"id":"2103.16854","title":"Facial Expression Recognition with Visual Transformers and Attentional Selective Fusion","created":"2021-03-31","cited_by_count":49},{"id":"2107.02341","title":"Feature Fusion Vision Transformer for Fine-Grained Visual Categorization","created":"2021-07-06","cited_by_count":40},{"id":"2212.05463","title":"Vision Transformer with Attentive Pooling for Robust Facial Expression Recognition","created":"2022-12-11","cited_by_count":35},{"id":"2107.08192","title":"RAMS-Trans: Recurrent Attention Multi-scale Transformer forFine-grained Image Recognition","created":"2021-07-17","cited_by_count":34},{"id":"2101.06635","title":"Context-aware Attentional Pooling (CAP) for Fine-grained Visual Classification","created":"2021-01-17","cited_by_count":31},{"id":"2106.04520","title":"MVT: Mask Vision Transformer for Facial Expression Recognition in the wild","created":"2021-06-08","cited_by_count":27},{"id":"1912.06842","title":"Fine-grained Recognition: Accounting for Subtle Differences between Similar Classes","created":"2019-12-14","cited_by_count":24},{"id":"2203.15987","title":"Fine-Grained Object Classification via Self-Supervised Pose Alignment","created":"2022-03-30","cited_by_count":22},{"id":"1801.09057","title":"Aligned to the Object, not to the Image: A Unified Pose-aligned Representation for Fine-grained Recognition","created":"2018-01-27","cited_by_count":10}],"next_cursor":null}