{"list":"other","total":56,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1411.4038","title":"Fully Convolutional Networks for Semantic Segmentation","created":"2014-11-14","cited_by_count":4859},{"id":"1802.02611","title":"Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation","created":"2018-02-07","cited_by_count":3223},{"id":"2105.15203","title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","created":"2021-05-31","cited_by_count":2940},{"id":"1612.01105","title":"Pyramid Scene Parsing Network","created":"2016-12-04","cited_by_count":2479},{"id":"1606.04797","title":"V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation","created":"2016-06-15","cited_by_count":2292},{"id":"2102.12122","title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","created":"2021-02-24","cited_by_count":1962},{"id":"1908.07919","title":"Deep High-Resolution Representation Learning for Visual Recognition","created":"2019-08-20","cited_by_count":1420},{"id":"2012.15840","title":"Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers","created":"2020-12-31","cited_by_count":1369},{"id":"2107.06278","title":"Per-Pixel Classification is Not All You Need for Semantic Segmentation","created":"2021-07-13","cited_by_count":1152},{"id":"1511.07122","title":"Multi-Scale Context Aggregation by Dilated Convolutions","created":"2015-11-23","cited_by_count":1133},{"id":"2101.11986","title":"Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet","created":"2021-01-28","cited_by_count":1101},{"id":"1809.02983","title":"Dual Attention Network for Scene Segmentation","created":"2018-09-09","cited_by_count":1003},{"id":"2105.05633","title":"Segmenter: Transformer for Semantic Segmentation","created":"2021-05-12","cited_by_count":855},{"id":"2106.13797","title":"PVT v2: Improved Baselines with Pyramid Vision Transformer","created":"2021-06-25","cited_by_count":751},{"id":"1808.00897","title":"BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation","created":"2018-08-02","cited_by_count":645},{"id":"2104.13840","title":"Twins: Revisiting the Design of Spatial Attention in Vision Transformers","created":"2021-04-28","cited_by_count":565},{"id":"2107.00652","title":"CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windows","created":"2021-07-01","cited_by_count":527},{"id":"2211.05778","title":"InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions","created":"2022-11-10","cited_by_count":482},{"id":"1708.00786","title":"Structure-measure: A New Way to Evaluate Foreground Maps","created":"2017-08-02","cited_by_count":480},{"id":"1611.06612","title":"RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentation","created":"2016-11-20","cited_by_count":465},{"id":"1702.01105","title":"Joint 2D-3D-Semantic Data for Indoor Scene Understanding","created":"2017-02-03","cited_by_count":406},{"id":"2012.00759","title":"MaX-DeepLab: End-to-End Panoptic Segmentation with Mask Transformers","created":"2020-12-01","cited_by_count":355},{"id":"1704.08545","title":"ICNet for Real-Time Semantic Segmentation on High-Resolution Images","created":"2017-04-27","cited_by_count":261},{"id":"2204.07143","title":"Neighborhood Attention Transformer","created":"2022-04-14","cited_by_count":239},{"id":"2007.09062","title":"Multi-scale Interactive Network for Salient Object Detection","created":"2020-07-17","cited_by_count":212},{"id":"1908.07678","title":"Asymmetric Non-local Neural Networks for Semantic Segmentation","created":"2019-08-21","cited_by_count":196},{"id":"2203.11926","title":"Focal Modulation Networks","created":"2022-03-22","cited_by_count":186},{"id":"2307.04767","title":"Semantic-SAM: Segment and Recognize Anything at Any Granularity","created":"2023-07-10","cited_by_count":185},{"id":"2104.12099","title":"Visual Saliency Transformer","created":"2021-04-25","cited_by_count":175},{"id":"2204.03645","title":"DaViT: Dual Attention Vision Transformers","created":"2022-04-07","cited_by_count":175},{"id":"2008.11048","title":"Label Decoupling Framework for Salient Object Detection","created":"2020-08-25","cited_by_count":111},{"id":"1806.05376","title":"Single Image Reflection Separation with Perceptual Losses","created":"2018-06-14","cited_by_count":98},{"id":"2003.13948","title":"Segmenting Transparent Objects in the Wild","created":"2020-03-31","cited_by_count":98},{"id":"1811.01206","title":"DUNet: A deformable network for retinal vessel segmentation","created":"2018-11-03","cited_by_count":90},{"id":"2004.08515","title":"JL-DCF: Joint Learning and Densely-Cooperative Fusion Framework for RGB-D Salient Object Detection","created":"2020-04-18","cited_by_count":79},{"id":"1808.03833","title":"Self-Supervised Model Adaptation for Multimodal Semantic Segmentation","created":"2018-08-11","cited_by_count":73},{"id":"2007.06227","title":"Hierarchical Dynamic Filtering Network for RGB-D Salient Object Detection","created":"2020-07-13","cited_by_count":72},{"id":"1806.01054","title":"RedNet: Residual Encoder-Decoder Network for indoor RGB-D Semantic Segmentation","created":"2018-06-04","cited_by_count":66},{"id":"1905.02423","title":"LEDNet: A Lightweight Encoder-Decoder Network for Real-Time Semantic Segmentation","created":"2019-05-07","cited_by_count":50},{"id":"2103.05687","title":"Capturing Omni-Range Context for Omnidirectional Segmentation","created":"2021-03-09","cited_by_count":50},{"id":"2103.15734","title":"Enhanced Boundary Learning for Glass-like Object Segmentation","created":"2021-03-29","cited_by_count":48},{"id":"2012.07131","title":"Location-aware Single Image Reflection Removal","created":"2020-12-13","cited_by_count":43},{"id":"2207.04526","title":"Efficient Multi-Task RGB-D Scene Analysis for Indoor Environments","created":"2022-07-10","cited_by_count":33},{"id":"2011.13313","title":"Polarization-driven Semantic Segmentation via Efficient Attention-bridged Fusion","created":"2020-11-26","cited_by_count":24},{"id":"2108.09174","title":"Trans4Trans: Efficient Transformer for Transparent Object and Semantic Scene Segmentation in Real-World Navigation Assistance","created":"2021-08-20","cited_by_count":22},{"id":"2305.16698","title":"Detect Any Shadow: Segment Anything for Video Shadow Detection","created":"2023-05-26","cited_by_count":16},{"id":"2211.15644","title":"Efficient Mirror Detection via Multi-level Heterogeneous Learning","created":"2022-11-28","cited_by_count":13},{"id":"2207.06332","title":"Symmetry-Aware Transformer-based Mirror Detection","created":"2022-07-13","cited_by_count":11},{"id":"2209.04639","title":"Large-Field Contextual Feature Learning for Glass Detection","created":"2022-09-10","cited_by_count":8},{"id":"2103.13279","title":"FakeMix Augmentation Improves Transparent Object Detection","created":"2021-03-24","cited_by_count":7}],"next_cursor":null}