{"list":"other","total":72,"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":"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":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1612.03144","title":"Feature Pyramid Networks for Object Detection","created":"2016-12-09","cited_by_count":5036},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"1504.08083","title":"Fast R-CNN","created":"2015-04-30","cited_by_count":2933},{"id":"1611.01144","title":"Categorical Reparameterization with Gumbel-Softmax","created":"2016-11-03","cited_by_count":2739},{"id":"1602.07332","title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","created":"2016-02-23","cited_by_count":2656},{"id":"1611.05431","title":"Aggregated Residual Transformations for Deep Neural Networks","created":"2016-11-16","cited_by_count":2546},{"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":"1908.03195","title":"LVIS: A Dataset for Large Vocabulary Instance Segmentation","created":"2019-08-08","cited_by_count":1217},{"id":"1904.07850","title":"Objects as Points","created":"2019-04-16","cited_by_count":1175},{"id":"1603.06937","title":"Stacked Hourglass Networks for Human Pose Estimation","created":"2016-03-22","cited_by_count":915},{"id":"1808.01244","title":"CornerNet: Detecting Objects as Paired Keypoints","created":"2018-08-03","cited_by_count":763},{"id":"1711.10485","title":"AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networks","created":"2017-11-28","cited_by_count":664},{"id":"2007.07314","title":"Long-tail learning via logit adjustment","created":"2020-07-14","cited_by_count":618},{"id":"1701.02426","title":"Scene Graph Generation by Iterative Message Passing","created":"2017-01-10","cited_by_count":462},{"id":"2110.04596","title":"Deep Long-Tailed Learning: A Survey","created":"2021-10-09","cited_by_count":417},{"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":"1804.01622","title":"Image Generation from Scene Graphs","created":"2018-04-04","cited_by_count":324},{"id":"1808.00191","title":"Graph R-CNN for Scene Graph Generation","created":"2018-08-01","cited_by_count":298},{"id":"1904.11490","title":"RepPoints: Point Set Representation for Object Detection","created":"2019-04-25","cited_by_count":264},{"id":"1812.01880","title":"Learning to Compose Dynamic Tree Structures for Visual Contexts","created":"2018-12-05","cited_by_count":259},{"id":"1812.02378","title":"Auto-Encoding Scene Graphs for Image Captioning","created":"2018-12-06","cited_by_count":255},{"id":"2205.09310","title":"Mitigating Neural Network Overconfidence with Logit Normalization","created":"2022-05-19","cited_by_count":252},{"id":"1912.06992","title":"Action Genome: Actions as Composition of Spatio-temporal Scene Graphs","created":"2019-12-15","cited_by_count":250},{"id":"1702.05448","title":"Learning to Detect Human-Object Interactions","created":"2017-02-17","cited_by_count":240},{"id":"1809.07041","title":"Exploring Visual Relationship for Image Captioning","created":"2018-09-19","cited_by_count":215},{"id":"2103.16370","title":"Distribution Alignment: A Unified Framework for Long-tail Visual Recognition","created":"2021-03-30","cited_by_count":198},{"id":"2006.09214","title":"FCOS: A simple and strong anchor-free object detector","created":"2020-06-14","cited_by_count":171},{"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":"2104.00308","title":"Bipartite Graph Network with Adaptive Message Passing for Unbiased Scene Graph Generation","created":"2021-04-01","cited_by_count":137},{"id":"2104.01111","title":"A Comprehensive Survey of Scene Graphs: Generation and Application","created":"2021-03-17","cited_by_count":125},{"id":"1609.05600","title":"Graph-Structured Representations for Visual Question Answering","created":"2016-09-19","cited_by_count":123},{"id":"2207.11247","title":"Panoptic Scene Graph Generation","created":"2022-07-22","cited_by_count":114},{"id":"2103.02221","title":"Energy-Based Learning for Scene Graph Generation","created":"2021-03-03","cited_by_count":104},{"id":"2112.12970","title":"SGTR: End-to-end Scene Graph Generation with Transformer","created":"2021-12-24","cited_by_count":103},{"id":"1903.02728","title":"Graphical Contrastive Losses for Scene Graph Parsing","created":"2019-03-07","cited_by_count":100},{"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":"2001.02314","title":"Bridging Knowledge Graphs to Generate Scene Graphs","created":"2020-01-07","cited_by_count":86},{"id":"2009.00893","title":"PCPL: Predicate-Correlation Perception Learning for Unbiased Scene Graph Generation","created":"2020-09-02","cited_by_count":75},{"id":"2107.02112","title":"Recovering the Unbiased Scene Graphs from the Biased Ones","created":"2021-07-05","cited_by_count":71},{"id":"2108.09668","title":"Learning of Visual Relations: The Devil is in the Tails","created":"2021-08-22","cited_by_count":65},{"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":"1706.07365","title":"Pixels to Graphs by Associative Embedding","created":"2017-06-22","cited_by_count":58},{"id":"2103.16083","title":"Fully Convolutional Scene Graph Generation","created":"2021-03-30","cited_by_count":57},{"id":"2203.11654","title":"Fine-Grained Scene Graph Generation with Data Transfer","created":"2022-03-22","cited_by_count":57},{"id":"2108.13129","title":"From General to Specific: Informative Scene Graph Generation via Balance Adjustment","created":"2021-08-30","cited_by_count":51},{"id":"1811.06410","title":"LinkNet: Relational Embedding for Scene Graph","created":"2018-11-15","cited_by_count":45},{"id":"2106.10815","title":"Structured Sparse R-CNN for Direct Scene Graph Generation","created":"2021-06-21","cited_by_count":44},{"id":"2005.08230","title":"Graph Density-Aware Losses for Novel Compositions in Scene Graph Generation","created":"2020-05-17","cited_by_count":31},{"id":"2105.02170","title":"Visual Relationship Detection Using Part-and-Sum Transformers with Composite Queries","created":"2021-05-05","cited_by_count":31},{"id":"2204.02597","title":"Fine-Grained Predicates Learning for Scene Graph Generation","created":"2022-04-06","cited_by_count":27},{"id":"2006.07585","title":"Learning from the Scene and Borrowing from the Rich: Tackling the Long Tail in Scene Graph Generation","created":"2020-06-13","cited_by_count":22},{"id":"2201.06794","title":"Resistance Training using Prior Bias: toward Unbiased Scene Graph Generation","created":"2022-01-18","cited_by_count":22},{"id":"2105.11731","title":"ST-HOI: A Spatial-Temporal Baseline for Human-Object Interaction Detection in Videos","created":"2021-05-25","cited_by_count":20},{"id":"2008.07832","title":"Tackling the Unannotated: Scene Graph Generation with Bias-Reduced Models","created":"2020-08-18","cited_by_count":19},{"id":"2109.05346","title":"BGT-Net: Bidirectional GRU Transformer Network for Scene Graph Generation","created":"2021-09-11","cited_by_count":18},{"id":"2104.11934","title":"RelTransformer: A Transformer-Based Long-Tail Visual Relationship Recognition","created":"2021-04-24","cited_by_count":9},{"id":"1905.00966","title":"Improving Visual Relation Detection using Depth Maps","created":"2019-05-02","cited_by_count":8},{"id":"2306.05689","title":"Single-Stage Visual Relationship Learning using Conditional Queries","created":"2023-06-09","cited_by_count":7},{"id":"2201.11697","title":"Constrained Structure Learning for Scene Graph Generation","created":"2022-01-27","cited_by_count":3}],"next_cursor":null}