{"list":"other","total":63,"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":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"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":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"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":"1612.03144","title":"Feature Pyramid Networks for Object Detection","created":"2016-12-09","cited_by_count":5036},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"1802.02611","title":"Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation","created":"2018-02-07","cited_by_count":3223},{"id":"2112.01527","title":"Masked-attention Mask Transformer for Universal Image Segmentation","created":"2021-12-02","cited_by_count":2351},{"id":"1606.04797","title":"V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation","created":"2016-06-15","cited_by_count":2292},{"id":"1906.07155","title":"MMDetection: Open MMLab Detection Toolbox and Benchmark","created":"2019-06-17","cited_by_count":1385},{"id":"2107.06278","title":"Per-Pixel Classification is Not All You Need for Semantic Segmentation","created":"2021-07-13","cited_by_count":1152},{"id":"1811.11168","title":"Deformable ConvNets v2: More Deformable, Better Results","created":"2018-11-27","cited_by_count":670},{"id":"1901.02446","title":"Panoptic Feature Pyramid Networks","created":"2019-01-08","cited_by_count":645},{"id":"2011.12450","title":"Sparse R-CNN: End-to-End Object Detection with Learnable Proposals","created":"2020-11-25","cited_by_count":495},{"id":"1901.07518","title":"Hybrid Task Cascade for Instance Segmentation","created":"2019-01-22","cited_by_count":481},{"id":"1904.02689","title":"YOLACT: Real-time Instance Segmentation","created":"2019-04-04","cited_by_count":443},{"id":"2011.14503","title":"End-to-End Video Instance Segmentation with Transformers","created":"2020-11-30","cited_by_count":443},{"id":"2012.00759","title":"MaX-DeepLab: End-to-End Panoptic Segmentation with Mask Transformers","created":"2020-12-01","cited_by_count":355},{"id":"2003.05664","title":"Conditional Convolutions for Instance Segmentation","created":"2020-03-12","cited_by_count":314},{"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":"1504.07889","title":"Bilinear CNNs for Fine-grained Visual Recognition","created":"2015-04-29","cited_by_count":228},{"id":"2106.14855","title":"K-Net: Towards Unified Image Segmentation","created":"2021-06-28","cited_by_count":212},{"id":"1407.1808","title":"Simultaneous Detection and Segmentation","created":"2014-07-07","cited_by_count":159},{"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":"2203.15102","title":"Rethinking Semantic Segmentation: A Prototype View","created":"2022-03-28","cited_by_count":140},{"id":"1808.00157","title":"Instance-level Human Parsing via Part Grouping Network","created":"2018-08-01","cited_by_count":134},{"id":"1803.08225","title":"PersonLab: Person Pose Estimation and Instance Segmentation with a Bottom-Up, Part-Based, Geometric Embedding Model","created":"2018-03-22","cited_by_count":133},{"id":"1708.02551","title":"Semantic Instance Segmentation with a Discriminative Loss Function","created":"2017-08-08","cited_by_count":118},{"id":"1407.3867","title":"Part-based R-CNNs for Fine-grained Category Detection","created":"2014-07-15","cited_by_count":109},{"id":"1903.12174","title":"TensorMask: A Foundation for Dense Object Segmentation","created":"2019-03-28","cited_by_count":101},{"id":"2007.10035","title":"Improving Semantic Segmentation via Decoupled Body and Edge Supervision","created":"2020-07-20","cited_by_count":99},{"id":"1906.11109","title":"Instance Segmentation by Jointly Optimizing Spatial Embeddings and Clustering Bandwidth","created":"2019-06-26","cited_by_count":89},{"id":"2201.05047","title":"TransVOD: End-to-End Video Object Detection with Spatial-Temporal Transformers","created":"2022-01-13","cited_by_count":78},{"id":"2106.02351","title":"SOLQ: Segmenting Objects by Learning Queries","created":"2021-06-04","cited_by_count":68},{"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":"1809.05996","title":"Devil in the Details: Towards Accurate Single and Multiple Human Parsing","created":"2018-09-17","cited_by_count":64},{"id":"1804.03287","title":"Understanding Humans in Crowded Scenes: Deep Nested Adversarial Learning and A New Benchmark for Multi-Human Parsing","created":"2018-04-10","cited_by_count":60},{"id":"1806.05372","title":"Multi-Attention Multi-Class Constraint for Fine-grained Image Recognition","created":"2018-06-14","cited_by_count":58},{"id":"2004.12276","title":"Fashionpedia: Ontology, Segmentation, and an Attribute Localization Dataset","created":"2020-04-26","cited_by_count":57},{"id":"1811.12596","title":"Parsing R-CNN for Instance-Level Human Analysis","created":"2018-11-30","cited_by_count":53},{"id":"1912.05027","title":"SpineNet: Learning Scale-Permuted Backbone for Recognition and Localization","created":"2019-12-10","cited_by_count":50},{"id":"2003.04262","title":"Cascaded Human-Object Interaction Recognition","created":"2020-03-09","cited_by_count":40},{"id":"2009.09447","title":"Renovating Parsing R-CNN for Accurate Multiple Human Parsing","created":"2020-09-20","cited_by_count":37},{"id":"1603.08678","title":"Instance-sensitive Fully Convolutional Networks","created":"2016-03-29","cited_by_count":36},{"id":"2001.06804","title":"Learning Compositional Neural Information Fusion for Human Parsing","created":"2020-01-19","cited_by_count":36},{"id":"2112.02582","title":"PolyphonicFormer: Unified Query Learning for Depth-aware Video Panoptic Segmentation","created":"2021-12-05","cited_by_count":36},{"id":"1807.01394","title":"ModaNet: A Large-Scale Street Fashion Dataset with Polygon Annotations","created":"2018-07-03","cited_by_count":33},{"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":"1912.09622","title":"Learning Semantic Neural Tree for Human Parsing","created":"2019-12-20","cited_by_count":29},{"id":"1805.04310","title":"Weakly and Semi Supervised Human Body Part Parsing via Pose-Guided Knowledge Transfer","created":"2018-05-11","cited_by_count":27},{"id":"1811.10870","title":"Affinity Derivation and Graph Merge for Instance Segmentation","created":"2018-11-27","cited_by_count":25},{"id":"1909.07229","title":"Global Aggregation then Local Distribution in Fully Convolutional Networks","created":"2019-09-16","cited_by_count":22},{"id":"1502.00739","title":"Clothing Co-Parsing by Joint Image Segmentation and Labeling","created":"2015-02-03","cited_by_count":20},{"id":"1709.03612","title":"Holistic, Instance-Level Human Parsing","created":"2017-09-11","cited_by_count":19},{"id":"1801.01260","title":"Cross-domain Human Parsing via Adversarial Feature and Label Adaptation","created":"2018-01-04","cited_by_count":11}],"next_cursor":null}