{"list":"other","total":54,"rows":[{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"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":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"2203.00667","title":"Generative Adversarial Networks","created":"2022-03-01","cited_by_count":5627},{"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":"1506.02640","title":"You Only Look Once: Unified, Real-Time Object Detection","created":"2015-06-08","cited_by_count":4852},{"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":"1512.02325","title":"SSD: Single Shot MultiBox Detector","created":"2015-12-08","cited_by_count":3130},{"id":"1804.02767","title":"YOLOv3: An Incremental Improvement","created":"2018-04-08","cited_by_count":2659},{"id":"1612.01105","title":"Pyramid Scene Parsing Network","created":"2016-12-04","cited_by_count":2479},{"id":"1711.07971","title":"Non-local Neural Networks","created":"2017-11-21","cited_by_count":2293},{"id":"1904.01355","title":"FCOS: Fully Convolutional One-Stage Object Detection","created":"2019-04-02","cited_by_count":1577},{"id":"1803.08494","title":"Group Normalization","created":"2018-03-22","cited_by_count":1524},{"id":"1612.08242","title":"YOLO9000: Better, Faster, Stronger","created":"2016-12-25","cited_by_count":1431},{"id":"1904.07850","title":"Objects as Points","created":"2019-04-16","cited_by_count":1175},{"id":"1808.01244","title":"CornerNet: Detecting Objects as Paired Keypoints","created":"2018-08-03","cited_by_count":763},{"id":"1708.02002","title":"Focal Loss for Dense Object Detection","created":"2017-08-07","cited_by_count":752},{"id":"1909.11065","title":"Segmentation Transformer: Object-Contextual Representations for Semantic Segmentation","created":"2019-09-24","cited_by_count":576},{"id":"1802.00434","title":"DensePose: Dense Human Pose Estimation In The Wild","created":"2018-02-01","cited_by_count":575},{"id":"1901.07518","title":"Hybrid Task Cascade for Instance Segmentation","created":"2019-01-22","cited_by_count":481},{"id":"1903.00241","title":"Mask Scoring R-CNN","created":"2019-03-01","cited_by_count":266},{"id":"1802.08122","title":"Harmonious Attention Network for Person Re-Identification","created":"2018-02-22","cited_by_count":211},{"id":"1608.01471","title":"UnitBox: An Advanced Object Detection Network","created":"2016-08-04","cited_by_count":205},{"id":"1911.06667","title":"CenterMask : Real-Time Anchor-Free Instance Segmentation","created":"2019-11-15","cited_by_count":201},{"id":"1704.07333","title":"Detecting and Recognizing Human-Object Interactions","created":"2017-04-24","cited_by_count":199},{"id":"1611.07715","title":"Deep Feature Flow for Video Recognition","created":"2016-11-23","cited_by_count":186},{"id":"1910.09777","title":"Self-Correction for Human Parsing","created":"2019-10-22","cited_by_count":180},{"id":"1703.10025","title":"Flow-Guided Feature Aggregation for Video Object Detection","created":"2017-03-29","cited_by_count":177},{"id":"1808.07962","title":"Learning Human-Object Interactions by Graph Parsing Neural Networks","created":"2018-08-23","cited_by_count":176},{"id":"1907.05740","title":"Gated-SCNN: Gated Shape CNNs for Semantic Segmentation","created":"2019-07-12","cited_by_count":166},{"id":"1901.08043","title":"Bottom-up Object Detection by Grouping Extreme and Center Points","created":"2019-01-23","cited_by_count":156},{"id":"2001.00309","title":"BlendMask: Top-Down Meets Bottom-Up for Instance Segmentation","created":"2020-01-02","cited_by_count":145},{"id":"1808.00157","title":"Instance-level Human Parsing via Part Grouping Network","created":"2018-08-01","cited_by_count":134},{"id":"1909.00179","title":"Boundary-Aware Feature Propagation for Scene Segmentation","created":"2019-08-31","cited_by_count":107},{"id":"1902.11026","title":"Towards Multi-pose Guided Virtual Try-on Network","created":"2019-02-28","cited_by_count":95},{"id":"2203.14335","title":"Deep Hierarchical Semantic Segmentation","created":"2022-03-27","cited_by_count":84},{"id":"1904.04536","title":"Graphonomy: Universal Human Parsing via Graph Transfer Learning","created":"2019-04-09","cited_by_count":81},{"id":"2007.08921","title":"Boundary-preserving Mask R-CNN","created":"2020-07-17","cited_by_count":74},{"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":"1509.04874","title":"DenseBox: Unifying Landmark Localization with End to End Object Detection","created":"2015-09-16","cited_by_count":58},{"id":"1811.12596","title":"Parsing R-CNN for Instance-Level Human Analysis","created":"2018-11-30","cited_by_count":53},{"id":"2003.04845","title":"Hierarchical Human Parsing with Typed Part-Relation Reasoning","created":"2020-03-10","cited_by_count":38},{"id":"2009.09447","title":"Renovating Parsing R-CNN for Accurate Multiple Human Parsing","created":"2020-09-20","cited_by_count":37},{"id":"1808.00661","title":"Adaptive Temporal Encoding Network for Video Instance-level Human Parsing","created":"2018-08-02","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":"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":"1911.12053","title":"Grapy-ML: Graph Pyramid Mutual Learning for Cross-dataset Human Parsing","created":"2019-11-27","cited_by_count":23},{"id":"2005.01431","title":"Correlating Edge, Pose with Parsing","created":"2020-05-04","cited_by_count":18},{"id":"2203.03145","title":"End-to-end video instance segmentation via spatial-temporal graph neural networks","created":"2022-03-07","cited_by_count":16},{"id":"2010.12176","title":"Delving into the Cyclic Mechanism in Semi-supervised Video Object Segmentation","created":"2020-10-23","cited_by_count":15}],"next_cursor":null}