{"list":"other","total":72,"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":"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":"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":"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":"2201.03545","title":"A ConvNet for the 2020s","created":"2022-01-10","cited_by_count":3579},{"id":"1606.00915","title":"DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs","created":"2016-06-02","cited_by_count":3241},{"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":"1611.01144","title":"Categorical Reparameterization with Gumbel-Softmax","created":"2016-11-03","cited_by_count":2739},{"id":"2112.01527","title":"Masked-attention Mask Transformer for Universal Image Segmentation","created":"2021-12-02","cited_by_count":2351},{"id":"1711.07971","title":"Non-local Neural Networks","created":"2017-11-21","cited_by_count":2293},{"id":"1906.07155","title":"MMDetection: Open MMLab Detection Toolbox and Benchmark","created":"2019-06-17","cited_by_count":1385},{"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":"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":"1801.00868","title":"Panoptic Segmentation","created":"2018-01-03","cited_by_count":802},{"id":"1901.02446","title":"Panoptic Feature Pyramid Networks","created":"2019-01-08","cited_by_count":645},{"id":"1901.07518","title":"Hybrid Task Cascade for Instance Segmentation","created":"2019-01-22","cited_by_count":481},{"id":"1912.08193","title":"PointRend: Image Segmentation as Rendering","created":"2019-12-17","cited_by_count":440},{"id":"1906.09756","title":"Cascade R-CNN: High Quality Object Detection and Instance Segmentation","created":"2019-06-24","cited_by_count":429},{"id":"1409.5185","title":"Deeply-Supervised Nets","created":"2014-09-18","cited_by_count":367},{"id":"1910.04751","title":"Panoptic-DeepLab","created":"2019-10-10","cited_by_count":363},{"id":"2012.00759","title":"MaX-DeepLab: End-to-End Panoptic Segmentation with Mask Transformers","created":"2020-12-01","cited_by_count":355},{"id":"2003.07853","title":"Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation","created":"2020-03-17","cited_by_count":326},{"id":"1912.04488","title":"SOLO: Segmenting Objects by Locations","created":"2019-12-10","cited_by_count":289},{"id":"1903.00241","title":"Mask Scoring R-CNN","created":"2019-03-01","cited_by_count":266},{"id":"2101.11939","title":"Exploring Cross-Image Pixel Contrast for Semantic Segmentation","created":"2021-01-28","cited_by_count":242},{"id":"1502.03240","title":"Conditional Random Fields as Recurrent Neural Networks","created":"2015-02-11","cited_by_count":214},{"id":"2106.14855","title":"K-Net: Towards Unified Image Segmentation","created":"2021-06-28","cited_by_count":212},{"id":"1901.03784","title":"UPSNet: A Unified Panoptic Segmentation Network","created":"2019-01-12","cited_by_count":175},{"id":"2105.01928","title":"Instances as Queries","created":"2021-05-05","cited_by_count":158},{"id":"2001.00309","title":"BlendMask: Top-Down Meets Bottom-Up for Instance Segmentation","created":"2020-01-02","cited_by_count":145},{"id":"2109.03814","title":"Panoptic SegFormer: Delving Deeper into Panoptic Segmentation with Transformers","created":"2021-09-08","cited_by_count":109},{"id":"1903.12174","title":"TensorMask: A Foundation for Dense Object Segmentation","created":"2019-03-28","cited_by_count":101},{"id":"2012.00720","title":"Fully Convolutional Networks for Panoptic Segmentation","created":"2020-12-01","cited_by_count":92},{"id":"2111.01236","title":"Multi-Scale High-Resolution Vision Transformer for Semantic Segmentation","created":"2021-11-01","cited_by_count":92},{"id":"1906.11109","title":"Instance Segmentation by Jointly Optimizing Spatial Embeddings and Clustering Bandwidth","created":"2019-06-26","cited_by_count":89},{"id":"2103.10284","title":"SG-Net: Spatial Granularity Network for One-Stage Video Instance Segmentation","created":"2021-03-18","cited_by_count":87},{"id":"2210.02025","title":"GMMSeg: Gaussian Mixture based Generative Semantic Segmentation Models","created":"2022-10-05","cited_by_count":87},{"id":"1807.10174","title":"Superpixel Sampling Networks","created":"2018-07-26","cited_by_count":79},{"id":"1611.08303","title":"Deep Watershed Transform for Instance Segmentation","created":"2016-11-24","cited_by_count":78},{"id":"2003.12929","title":"Superpixel Segmentation with Fully Convolutional Networks","created":"2020-03-29","cited_by_count":72},{"id":"1812.03904","title":"Attention-guided Unified Network for Panoptic Segmentation","created":"2018-12-10","cited_by_count":71},{"id":"2106.02351","title":"SOLQ: Segmenting Objects by Learning Queries","created":"2021-06-04","cited_by_count":68},{"id":"2203.12827","title":"Sparse Instance Activation for Real-Time Instance Segmentation","created":"2022-03-24","cited_by_count":63},{"id":"2206.08948","title":"CMT-DeepLab: Clustering Mask Transformers for Panoptic Segmentation","created":"2022-06-17","cited_by_count":60},{"id":"2209.07383","title":"Visual Recognition with Deep Nearest Centroids","created":"2022-09-15","cited_by_count":59},{"id":"1712.08273","title":"Recurrent Pixel Embedding for Instance Grouping","created":"2017-12-22","cited_by_count":58},{"id":"2207.04718","title":"Physical Attack on Monocular Depth Estimation with Optimal Adversarial Patches","created":"2022-07-11","cited_by_count":57},{"id":"1712.04837","title":"MaskLab: Instance Segmentation by Refining Object Detection with Semantic and Direction Features","created":"2017-12-13","cited_by_count":54},{"id":"1612.01601","title":"Superpixels: An Evaluation of the State-of-the-Art","created":"2016-12-06","cited_by_count":52},{"id":"2105.00637","title":"ISTR: End-to-End Instance Segmentation with Transformers","created":"2021-05-03","cited_by_count":52},{"id":"1611.08272","title":"InstanceCut: from Edges to Instances with MultiCut","created":"2016-11-24","cited_by_count":49},{"id":"1903.05027","title":"An End-to-End Network for Panoptic Segmentation","created":"2019-03-12","cited_by_count":46},{"id":"2108.06747","title":"SOTR: Segmenting Objects with Transformers","created":"2021-08-15","cited_by_count":42},{"id":"2001.04982","title":"Unifying Training and Inference for Panoptic Segmentation","created":"2020-01-14","cited_by_count":37},{"id":"2012.02366","title":"DenserNet: Weakly Supervised Visual Localization Using Multi-scale Feature Aggregation","created":"2020-12-04","cited_by_count":33},{"id":"1708.04607","title":"Segmentation-Aware Convolutional Networks Using Local Attention Masks","created":"2017-08-15","cited_by_count":31},{"id":"2103.04570","title":"Differentiable Multi-Granularity Human Representation Learning for Instance-Aware Human Semantic Parsing","created":"2021-03-08","cited_by_count":31},{"id":"1906.05896","title":"Learning Instance Occlusion for Panoptic Segmentation","created":"2019-06-13","cited_by_count":30},{"id":"2210.00911","title":"Learning Equivariant Segmentation with Instance-Unique Querying","created":"2022-10-03","cited_by_count":17},{"id":"2301.13487","title":"Adversarial Training of Self-supervised Monocular Depth Estimation against Physical-World Attacks","created":"2023-01-31","cited_by_count":17},{"id":"2107.14209","title":"A Unified Efficient Pyramid Transformer for Semantic Segmentation","created":"2021-07-29","cited_by_count":14},{"id":"2103.10681","title":"Learning the Superpixel in a Non-iterative and Lifelong Manner","created":"2021-03-19","cited_by_count":12},{"id":"2004.01849","title":"Pixel Consensus Voting for Panoptic Segmentation","created":"2020-04-04","cited_by_count":10}],"next_cursor":null}