{"list":"other","total":59,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"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":"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":"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":"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":"1311.2524","title":"Rich feature hierarchies for accurate object detection and semantic segmentation","created":"2013-11-11","cited_by_count":2162},{"id":"1904.01355","title":"FCOS: Fully Convolutional One-Stage Object Detection","created":"2019-04-02","cited_by_count":1577},{"id":"1706.02677","title":"Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour","created":"2017-06-08","cited_by_count":1492},{"id":"1703.06211","title":"Deformable Convolutional Networks","created":"2017-03-17","cited_by_count":1488},{"id":"1908.07919","title":"Deep High-Resolution Representation Learning for Visual Recognition","created":"2019-08-20","cited_by_count":1420},{"id":"1902.09212","title":"Deep High-Resolution Representation Learning for Human Pose Estimation","created":"2019-02-25","cited_by_count":1339},{"id":"1908.03195","title":"LVIS: A Dataset for Large Vocabulary Instance Segmentation","created":"2019-08-08","cited_by_count":1217},{"id":"1801.00868","title":"Panoptic Segmentation","created":"2018-01-03","cited_by_count":802},{"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":"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":"1804.06208","title":"Simple Baselines for Human Pose Estimation and Tracking","created":"2018-04-17","cited_by_count":502},{"id":"2004.08955","title":"ResNeSt: Split-Attention Networks","created":"2020-04-19","cited_by_count":445},{"id":"1905.04804","title":"Video Instance Segmentation","created":"2019-05-12","cited_by_count":393},{"id":"1711.07319","title":"Cascaded Pyramid Network for Multi-Person Pose Estimation","created":"2017-11-20","cited_by_count":341},{"id":"1602.00134","title":"Convolutional Pose Machines","created":"2016-01-30","cited_by_count":325},{"id":"1903.00241","title":"Mask Scoring R-CNN","created":"2019-03-01","cited_by_count":266},{"id":"1910.09777","title":"Self-Correction for Human Parsing","created":"2019-10-22","cited_by_count":180},{"id":"1511.03339","title":"Attention to Scale: Scale-aware Semantic Image Segmentation","created":"2015-11-10","cited_by_count":169},{"id":"1808.00157","title":"Instance-level Human Parsing via Part Grouping Network","created":"2018-08-01","cited_by_count":134},{"id":"2003.11339","title":"Data Uncertainty Learning in Face Recognition","created":"2020-03-25","cited_by_count":134},{"id":"2003.09373","title":"SER-FIQ: Unsupervised Estimation of Face Image Quality Based on Stochastic Embedding Robustness","created":"2020-03-20","cited_by_count":112},{"id":"1711.05611","title":"Interpreting Deep Visual Representations via Network Dissection","created":"2017-11-15","cited_by_count":103},{"id":"2012.05258","title":"ViP-DeepLab: Learning Visual Perception with Depth-aware Video Panoptic Segmentation","created":"2020-12-09","cited_by_count":96},{"id":"1904.04536","title":"Graphonomy: Universal Human Parsing via Graph Transfer Learning","created":"2019-04-09","cited_by_count":81},{"id":"1804.01984","title":"Look into Person: Joint Body Parsing & Pose Estimation Network and A New Benchmark","created":"2018-04-05","cited_by_count":79},{"id":"1711.07240","title":"MegDet: A Large Mini-Batch Object Detector","created":"2017-11-20","cited_by_count":66},{"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":"1811.12596","title":"Parsing R-CNN for Instance-Level Human Analysis","created":"2018-11-30","cited_by_count":53},{"id":"1912.05891","title":"SetRank: Learning a Permutation-Invariant Ranking Model for Information Retrieval","created":"2019-12-12","cited_by_count":48},{"id":"1708.03383","title":"Joint Multi-Person Pose Estimation and Semantic Part Segmentation","created":"2017-08-10","cited_by_count":41},{"id":"1811.12026","title":"Attacks on State-of-the-Art Face Recognition using Attentional Adversarial Attack Generative Network","created":"2018-11-29","cited_by_count":38},{"id":"2003.04845","title":"Hierarchical Human Parsing with Typed Part-Relation Reasoning","created":"2020-03-10","cited_by_count":38},{"id":"2003.10152","title":"SOLOv2: Dynamic and Fast Instance Segmentation","created":"2020-03-23","cited_by_count":37},{"id":"2009.09447","title":"Renovating Parsing R-CNN for Accurate Multiple Human Parsing","created":"2020-09-20","cited_by_count":37},{"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":"1807.08260","title":"Macro-Micro Adversarial Network for Human Parsing","created":"2018-07-22","cited_by_count":28},{"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":"1511.04510","title":"Semantic Object Parsing with Local-Global Long Short-Term Memory","created":"2015-11-14","cited_by_count":16},{"id":"2004.08055","title":"Self-Learning with Rectification Strategy for Human Parsing","created":"2020-04-17","cited_by_count":12},{"id":"1504.01220","title":"Matching-CNN Meets KNN: Quasi-Parametric Human Parsing","created":"2015-04-06","cited_by_count":9},{"id":"2003.03570","title":"CPM R-CNN: Calibrating Point-guided Misalignment in Object Detection","created":"2020-03-07","cited_by_count":4}],"next_cursor":null}