{"list":"other","total":96,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"1612.00593","title":"PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation","created":"2016-12-02","cited_by_count":5248},{"id":"1411.4038","title":"Fully Convolutional Networks for Semantic Segmentation","created":"2014-11-14","cited_by_count":4859},{"id":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"id":"1502.01852","title":"Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification","created":"2015-02-06","cited_by_count":3611},{"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":"1711.07971","title":"Non-local Neural Networks","created":"2017-11-21","cited_by_count":2293},{"id":"1706.05587","title":"Rethinking Atrous Convolution for Semantic Image Segmentation","created":"2017-06-17","cited_by_count":2161},{"id":"1306.5151","title":"Fine-Grained Visual Classification of Aircraft","created":"2013-06-21","cited_by_count":1726},{"id":"2112.03857","title":"Grounded Language-Image Pre-training","created":"2021-12-07","cited_by_count":1156},{"id":"1801.00868","title":"Panoptic Segmentation","created":"2018-01-03","cited_by_count":802},{"id":"1812.02713","title":"PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understanding","created":"2018-12-06","cited_by_count":526},{"id":"2004.01804","title":"Google Landmarks Dataset v2 -- A Large-Scale Benchmark for Instance-Level Recognition and Retrieval","created":"2020-04-03","cited_by_count":309},{"id":"1406.2031","title":"Detect What You Can: Detecting and Representing Objects using Holistic Models and Body Parts","created":"2014-06-08","cited_by_count":232},{"id":"1504.07889","title":"Bilinear CNNs for Fine-grained Visual Recognition","created":"2015-04-29","cited_by_count":228},{"id":"2012.02046","title":"Neural Prototype Trees for Interpretable Fine-grained Image Recognition","created":"2020-12-03","cited_by_count":214},{"id":"1910.09777","title":"Self-Correction for Human Parsing","created":"2019-10-22","cited_by_count":180},{"id":"1806.06193","title":"Large Scale Fine-Grained Categorization and Domain-Specific Transfer Learning","created":"2018-06-16","cited_by_count":174},{"id":"1511.03339","title":"Attention to Scale: Scale-aware Semantic Image Segmentation","created":"2015-11-10","cited_by_count":169},{"id":"2103.16483","title":"Benchmarking Representation Learning for Natural World Image Collections","created":"2021-03-30","cited_by_count":168},{"id":"2103.05569","title":"FAIR1M: A Benchmark Dataset for Fine-grained Object Recognition in High-Resolution Remote Sensing Imagery","created":"2021-03-09","cited_by_count":143},{"id":"2111.06119","title":"Fine-Grained Image Analysis with Deep Learning: A Survey","created":"2021-11-11","cited_by_count":135},{"id":"1808.00157","title":"Instance-level Human Parsing via Part Grouping Network","created":"2018-08-01","cited_by_count":134},{"id":"1506.08959","title":"A Large-Scale Car Dataset for Fine-Grained Categorization and Verification","created":"2015-06-30","cited_by_count":130},{"id":"1407.3867","title":"Part-based R-CNNs for Fine-grained Category Detection","created":"2014-07-15","cited_by_count":109},{"id":"1906.05272","title":"Presence-Only Geographical Priors for Fine-Grained Image Classification","created":"2019-06-12","cited_by_count":109},{"id":"1809.00287","title":"Learning to Navigate for Fine-grained Classification","created":"2018-09-02","cited_by_count":103},{"id":"1804.00216","title":"Human Semantic Parsing for Person Re-identification","created":"2018-03-31","cited_by_count":100},{"id":"1905.01298","title":"SCOPS: Self-Supervised Co-Part Segmentation","created":"2019-05-03","cited_by_count":100},{"id":"1511.06062","title":"Compact Bilinear Pooling","created":"2015-11-19","cited_by_count":97},{"id":"1903.06150","title":"Looking for the Devil in the Details: Learning Trilinear Attention Sampling Network for Fine-grained Image Recognition","created":"2019-03-14","cited_by_count":95},{"id":"2002.10191","title":"Learning Attentive Pairwise Interaction for Fine-Grained Classification","created":"2020-02-24","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":"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":"2005.10411","title":"Interpretable and Accurate Fine-grained Recognition via Region Grouping","created":"2020-05-21","cited_by_count":75},{"id":"1903.06946","title":"Unsupervised Part-Based Disentangling of Object Shape and Appearance","created":"2019-03-16","cited_by_count":67},{"id":"1903.02827","title":"Weakly Supervised Complementary Parts Models for Fine-Grained Image Classification from the Bottom Up","created":"2019-03-07","cited_by_count":66},{"id":"1809.05934","title":"Maximum-Entropy Fine-Grained Classification","created":"2018-09-16","cited_by_count":65},{"id":"1809.05996","title":"Devil in the Details: Towards Accurate Single and Multiple Human Parsing","created":"2018-09-17","cited_by_count":64},{"id":"1612.02808","title":"3D Shape Segmentation with Projective Convolutional Networks","created":"2016-12-08","cited_by_count":63},{"id":"1512.08086","title":"Part-Stacked CNN for Fine-Grained Visual Categorization","created":"2015-12-26","cited_by_count":62},{"id":"1909.04412","title":"Cross-X Learning for Fine-Grained Visual Categorization","created":"2019-09-10","cited_by_count":61},{"id":"1806.05372","title":"Multi-Attention Multi-Class Constraint for Fine-grained Image Recognition","created":"2018-06-14","cited_by_count":58},{"id":"2111.06349","title":"Unsupervised Part Discovery from Contrastive Reconstruction","created":"2021-11-11","cited_by_count":57},{"id":"1809.03355","title":"Learning to Zoom: a Saliency-Based Sampling Layer for Neural Networks","created":"2018-09-10","cited_by_count":56},{"id":"2106.06351","title":"Part-aware Panoptic Segmentation","created":"2021-06-11","cited_by_count":56},{"id":"1704.01740","title":"Object-Part Attention Model for Fine-grained Image Classification","created":"2017-04-06","cited_by_count":54},{"id":"1811.12596","title":"Parsing R-CNN for Instance-Level Human Analysis","created":"2018-11-30","cited_by_count":53},{"id":"2004.05021","title":"Parsing-based View-aware Embedding Network for Vehicle Re-Identification","created":"2020-04-10","cited_by_count":53},{"id":"1909.11378","title":"Attention Convolutional Binary Neural Tree for Fine-Grained Visual Categorization","created":"2019-09-25","cited_by_count":51},{"id":"1807.09915","title":"Hierarchical Bilinear Pooling for Fine-Grained Visual Recognition","created":"2018-07-26","cited_by_count":47},{"id":"2003.05235","title":"Channel Interaction Networks for Fine-Grained Image Categorization","created":"2020-03-11","cited_by_count":47},{"id":"1603.07063","title":"Semantic Object Parsing with Graph LSTM","created":"2016-03-23","cited_by_count":44},{"id":"1604.04994","title":"Selective Convolutional Descriptor Aggregation for Fine-Grained Image Retrieval","created":"2016-04-18","cited_by_count":44},{"id":"1903.00709","title":"PartNet: A Recursive Part Decomposition Network for Fine-grained and Hierarchical Shape Segmentation","created":"2019-03-02","cited_by_count":44},{"id":"1611.05109","title":"Low-rank Bilinear Pooling for Fine-Grained Classification","created":"2016-11-16","cited_by_count":42},{"id":"1708.03383","title":"Joint Multi-Person Pose Estimation and Semantic Part Segmentation","created":"2017-08-10","cited_by_count":41},{"id":"2003.04845","title":"Hierarchical Human Parsing with Typed Part-Relation Reasoning","created":"2020-03-10","cited_by_count":38},{"id":"1808.00661","title":"Adaptive Temporal Encoding Network for Video Instance-level Human Parsing","created":"2018-08-02","cited_by_count":36},{"id":"1908.01313","title":"Low-Rank Pairwise Alignment Bilinear Network For Few-Shot Fine-Grained Image Classification","created":"2019-08-04","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":"2004.00705","title":"Revisiting Pose-Normalization for Fine-Grained Few-Shot Recognition","created":"2020-04-01","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":"2011.14311","title":"BSNet: Bi-Similarity Network for Few-shot Fine-grained Image Classification","created":"2020-11-29","cited_by_count":30},{"id":"1912.09622","title":"Learning Semantic Neural Tree for Human Parsing","created":"2019-12-20","cited_by_count":29},{"id":"2105.12405","title":"Unsupervised Part Segmentation through Disentangling Appearance and Shape","created":"2021-05-26","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":"2012.13975","title":"Power Normalizations in Fine-grained Image, Few-shot Image and Graph Classification","created":"2020-12-27","cited_by_count":27},{"id":"2007.09073","title":"GMNet: Graph Matching Network for Large Scale Part Semantic Segmentation in the Wild","created":"2020-07-17","cited_by_count":25},{"id":"2109.07894","title":"Heterogeneous Relational Complement for Vehicle Re-identification","created":"2021-09-16","cited_by_count":25},{"id":"1912.06842","title":"Fine-grained Recognition: Accounting for Subtle Differences between Similar Classes","created":"2019-12-14","cited_by_count":24},{"id":"1505.00276","title":"Joint Object and Part Segmentation using Deep Learned Potentials","created":"2015-05-01","cited_by_count":23},{"id":"1607.03738","title":"Do semantic parts emerge in Convolutional Neural Networks?","created":"2016-07-13","cited_by_count":23},{"id":"1911.12053","title":"Grapy-ML: Graph Pyramid Mutual Learning for Cross-dataset Human Parsing","created":"2019-11-27","cited_by_count":23},{"id":"1412.6124","title":"Semantic Part Segmentation using Compositional Model combining Shape and Appearance","created":"2014-12-18","cited_by_count":22},{"id":"1504.08289","title":"Neural Activation Constellations: Unsupervised Part Model Discovery with Convolutional Networks","created":"2015-04-30","cited_by_count":22},{"id":"1703.08580","title":"Deep Residual Learning for Instrument Segmentation in Robotic Surgery","created":"2017-03-24","cited_by_count":22},{"id":"1511.06881","title":"Zoom Better to See Clearer: Human and Object Parsing with Hierarchical Auto-Zoom Net","created":"2015-11-21","cited_by_count":21},{"id":"2003.14142","title":"Look-into-Object: Self-supervised Structure Modeling for Object Recognition","created":"2020-03-31","cited_by_count":20},{"id":"1512.02895","title":"Embedding Label Structures for Fine-Grained Feature Representation","created":"2015-12-09","cited_by_count":17},{"id":"1511.04510","title":"Semantic Object Parsing with Local-Global Long Short-Term Memory","created":"2015-11-14","cited_by_count":16},{"id":"2103.14098","title":"Learning Part Segmentation through Unsupervised Domain Adaptation from Synthetic Vehicles","created":"2021-03-25","cited_by_count":16},{"id":"1611.05709","title":"Factorized Bilinear Models for Image Recognition","created":"2016-11-17","cited_by_count":13},{"id":"2106.05897","title":"Unsupervised Co-part Segmentation through Assembly","created":"2021-06-10","cited_by_count":12},{"id":"2203.16168","title":"FLOAT: Factorized Learning of Object Attributes for Improved Multi-object Multi-part Scene Parsing","created":"2022-03-30","cited_by_count":9},{"id":"1809.05285","title":"Keypoint Based Weakly Supervised Human Parsing","created":"2018-09-14","cited_by_count":8},{"id":"2106.06485","title":"Pedestrian Attribute Recognition in Video Surveillance Scenarios Based on View-attribute Attention Localization","created":"2021-06-11","cited_by_count":8},{"id":"2108.04628","title":"Learning Canonical 3D Object Representation for Fine-Grained Recognition","created":"2021-08-10","cited_by_count":7},{"id":"1406.2375","title":"Parsing Semantic Parts of Cars Using Graphical Models and Segment Appearance Consistency","created":"2014-06-09","cited_by_count":5},{"id":"1707.00785","title":"Zero-Shot Fine-Grained Classification by Deep Feature Learning with Semantics","created":"2017-07-04","cited_by_count":3},{"id":"2201.09594","title":"Describe me if you can! Characterized Instance-level Human Parsing","created":"2022-01-24","cited_by_count":3},{"id":"2211.03003","title":"Learning to Annotate Part Segmentation with Gradient Matching","created":"2022-11-06","cited_by_count":3},{"id":"1807.07320","title":"Attend and Rectify: a Gated Attention Mechanism for Fine-Grained Recovery","created":"2018-07-19","cited_by_count":2},{"id":"2203.00441","title":"Bridge the Gap between Supervised and Unsupervised Learning for Fine-Grained Classification","created":"2022-03-01","cited_by_count":2}],"next_cursor":null}