{"list":"other","total":58,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"1602.07332","title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","created":"2016-02-23","cited_by_count":2656},{"id":"2112.01527","title":"Masked-attention Mask Transformer for Universal Image Segmentation","created":"2021-12-02","cited_by_count":2351},{"id":"2006.05525","title":"Knowledge Distillation: A Survey","created":"2020-06-09","cited_by_count":1603},{"id":"1901.05555","title":"Class-Balanced Loss Based on Effective Number of Samples","created":"2019-01-16","cited_by_count":1245},{"id":"2107.06278","title":"Per-Pixel Classification is Not All You Need for Semantic Segmentation","created":"2021-07-13","cited_by_count":1152},{"id":"1906.07413","title":"Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss","created":"2019-06-18","cited_by_count":989},{"id":"1612.03716","title":"COCO-Stuff: Thing and Stuff Classes in Context","created":"2016-12-12","cited_by_count":864},{"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":"1707.03237","title":"Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentations","created":"2017-07-11","cited_by_count":620},{"id":"1701.02426","title":"Scene Graph Generation by Iterative Message Passing","created":"2017-01-10","cited_by_count":462},{"id":"1711.06640","title":"Neural Motifs: Scene Graph Parsing with Global Context","created":"2017-11-17","cited_by_count":414},{"id":"2002.11949","title":"Unbiased Scene Graph Generation from Biased Training","created":"2020-02-27","cited_by_count":356},{"id":"1608.00187","title":"Visual Relationship Detection with Language Priors","created":"2016-07-31","cited_by_count":334},{"id":"1812.01880","title":"Learning to Compose Dynamic Tree Structures for Visual Contexts","created":"2018-12-05","cited_by_count":259},{"id":"2012.00321","title":"Disentangling Label Distribution for Long-tailed Visual Recognition","created":"2020-12-01","cited_by_count":172},{"id":"2003.12962","title":"GPS-Net: Graph Property Sensing Network for Scene Graph Generation","created":"2020-03-29","cited_by_count":166},{"id":"1903.03326","title":"Knowledge-Embedded Routing Network for Scene Graph Generation","created":"2019-03-08","cited_by_count":164},{"id":"1707.09700","title":"Scene Graph Generation from Objects, Phrases and Region Captions","created":"2017-07-31","cited_by_count":154},{"id":"2104.00308","title":"Bipartite Graph Network with Adaptive Message Passing for Unbiased Scene Graph Generation","created":"2021-04-01","cited_by_count":137},{"id":"2207.11247","title":"Panoptic Scene Graph Generation","created":"2022-07-22","cited_by_count":114},{"id":"1702.08319","title":"Visual Translation Embedding Network for Visual Relation Detection","created":"2017-02-27","cited_by_count":112},{"id":"1812.01855","title":"Explainable and Explicit Visual Reasoning over Scene Graphs","created":"2018-12-05","cited_by_count":103},{"id":"2112.12970","title":"SGTR: End-to-end Scene Graph Generation with Transformer","created":"2021-12-24","cited_by_count":103},{"id":"1904.00560","title":"Scene Graph Generation with External Knowledge and Image Reconstruction","created":"2019-04-01","cited_by_count":102},{"id":"1704.03114","title":"Detecting Visual Relationships with Deep Relational Networks","created":"2017-04-11","cited_by_count":97},{"id":"2201.11460","title":"RelTR: Relation Transformer for Scene Graph Generation","created":"2022-01-27","cited_by_count":96},{"id":"2003.00387","title":"Say As You Wish: Fine-grained Control of Image Caption Generation with Abstract Scene Graphs","created":"2020-03-01","cited_by_count":87},{"id":"1811.10696","title":"Attentive Relational Networks for Mapping Images to Scene Graphs","created":"2018-11-26","cited_by_count":73},{"id":"2201.00443","title":"Scene Graph Generation: A Comprehensive Survey","created":"2022-01-03","cited_by_count":73},{"id":"2107.02112","title":"Recovering the Unbiased Scene Graphs from the Biased Ones","created":"2021-07-05","cited_by_count":71},{"id":"2203.09811","title":"Stacked Hybrid-Attention and Group Collaborative Learning for Unbiased Scene Graph Generation","created":"2022-03-18","cited_by_count":67},{"id":"2203.10202","title":"Relationformer: A Unified Framework for Image-to-Graph Generation","created":"2022-03-19","cited_by_count":67},{"id":"2108.09668","title":"Learning of Visual Relations: The Devil is in the Tails","created":"2021-08-22","cited_by_count":65},{"id":"2009.07526","title":"CogTree: Cognition Tree Loss for Unbiased Scene Graph Generation","created":"2020-09-16","cited_by_count":62},{"id":"2206.03014","title":"The Devil is in the Labels: Noisy Label Correction for Robust Scene Graph Generation","created":"2022-06-07","cited_by_count":60},{"id":"2203.11654","title":"Fine-Grained Scene Graph Generation with Data Transfer","created":"2022-03-22","cited_by_count":57},{"id":"1812.02347","title":"Counterfactual Critic Multi-Agent Training for Scene Graph Generation","created":"2018-12-06","cited_by_count":53},{"id":"2108.13129","title":"From General to Specific: Informative Scene Graph Generation via Balance Adjustment","created":"2021-08-30","cited_by_count":51},{"id":"2007.01072","title":"Scene Graph Reasoning for Visual Question Answering","created":"2020-07-02","cited_by_count":50},{"id":"1804.10660","title":"Large-Scale Visual Relationship Understanding","created":"2018-04-27","cited_by_count":33},{"id":"2104.14207","title":"Segmentation-grounded Scene Graph Generation","created":"2021-04-29","cited_by_count":25},{"id":"2111.13517","title":"Not All Relations are Equal: Mining Informative Labels for Scene Graph Generation","created":"2021-11-26","cited_by_count":21},{"id":"2204.01969","title":"Region Rebalance for Long-Tailed Semantic Segmentation","created":"2022-04-05","cited_by_count":17},{"id":"1711.06032","title":"Natural Language Guided Visual Relationship Detection","created":"2017-11-16","cited_by_count":15},{"id":"2203.06907","title":"Hierarchical Memory Learning for Fine-Grained Scene Graph Generation","created":"2022-03-14","cited_by_count":15},{"id":"1809.00204","title":"Improving Visual Relationship Detection using Semantic Modeling of Scene Descriptions","created":"2018-09-01","cited_by_count":13},{"id":"2207.10936","title":"Long-tailed Instance Segmentation using Gumbel Optimized Loss","created":"2022-07-22","cited_by_count":12},{"id":"1905.00966","title":"Improving Visual Relation Detection using Depth Maps","created":"2019-05-02","cited_by_count":8},{"id":"2208.04165","title":"Neural Message Passing for Visual Relationship Detection","created":"2022-08-08","cited_by_count":6},{"id":"1911.09895","title":"Visual Relationship Detection with Low Rank Non-Negative Tensor Decomposition","created":"2019-11-22","cited_by_count":5},{"id":"2301.00351","title":"Skew Class-balanced Re-weighting for Unbiased Scene Graph Generation","created":"2023-01-01","cited_by_count":5}],"next_cursor":null}