{"list":"other","total":59,"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":"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":"1602.07332","title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","created":"2016-02-23","cited_by_count":2656},{"id":"1606.04797","title":"V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation","created":"2016-06-15","cited_by_count":2292},{"id":"1607.04606","title":"Enriching Word Vectors with Subword Information","created":"2016-07-15","cited_by_count":1583},{"id":"1906.07155","title":"MMDetection: Open MMLab Detection Toolbox and Benchmark","created":"2019-06-17","cited_by_count":1385},{"id":"2107.06278","title":"Per-Pixel Classification is Not All You Need for Semantic Segmentation","created":"2021-07-13","cited_by_count":1152},{"id":"1801.00868","title":"Panoptic Segmentation","created":"2018-01-03","cited_by_count":802},{"id":"1901.02446","title":"Panoptic Feature Pyramid Networks","created":"2019-01-08","cited_by_count":645},{"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":"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":"1812.01880","title":"Learning to Compose Dynamic Tree Structures for Visual Contexts","created":"2018-12-05","cited_by_count":259},{"id":"1702.05448","title":"Learning to Detect Human-Object Interactions","created":"2017-02-17","cited_by_count":240},{"id":"2106.14855","title":"K-Net: Towards Unified Image Segmentation","created":"2021-06-28","cited_by_count":212},{"id":"1704.07333","title":"Detecting and Recognizing Human-Object Interactions","created":"2017-04-24","cited_by_count":199},{"id":"1505.04474","title":"Visual Semantic Role Labeling","created":"2015-05-17","cited_by_count":190},{"id":"2104.13682","title":"HOTR: End-to-End Human-Object Interaction Detection with Transformers","created":"2021-04-28","cited_by_count":183},{"id":"1901.03784","title":"UPSNet: A Unified Panoptic Segmentation Network","created":"2019-01-12","cited_by_count":175},{"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":"2103.05399","title":"QPIC: Query-Based Pairwise Human-Object Interaction Detection with Image-Wide Contextual Information","created":"2021-03-09","cited_by_count":147},{"id":"2103.04503","title":"End-to-End Human Object Interaction Detection with HOI Transformer","created":"2021-03-08","cited_by_count":135},{"id":"2007.12407","title":"Visual Compositional Learning for Human-Object Interaction Detection","created":"2020-07-24","cited_by_count":130},{"id":"2008.11714","title":"DRG: Dual Relation Graph for Human-Object Interaction Detection","created":"2020-08-26","cited_by_count":117},{"id":"1702.08319","title":"Visual Translation Embedding Network for Visual Relation Detection","created":"2017-02-27","cited_by_count":112},{"id":"2003.14023","title":"Learning Human-Object Interaction Detection using Interaction Points","created":"2020-03-31","cited_by_count":108},{"id":"2103.02221","title":"Energy-Based Learning for Scene Graph Generation","created":"2021-03-03","cited_by_count":104},{"id":"1812.01855","title":"Explainable and Explicit Visual Reasoning over Scene Graphs","created":"2018-12-05","cited_by_count":103},{"id":"2108.05077","title":"Mining the Benefits of Two-stage and One-stage HOI Detection","created":"2021-08-11","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":"2004.08154","title":"Detailed 2D-3D Joint Representation for Human-Object Interaction","created":"2020-04-17","cited_by_count":93},{"id":"2112.01838","title":"Efficient Two-Stage Detection of Human-Object Interactions with a Novel Unary-Pairwise Transformer","created":"2021-12-03","cited_by_count":91},{"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":"2001.02314","title":"Bridging Knowledge Graphs to Generate Scene Graphs","created":"2020-01-07","cited_by_count":86},{"id":"2004.03677","title":"Semantic Image Manipulation Using Scene Graphs","created":"2020-04-07","cited_by_count":82},{"id":"2104.02867","title":"Affordance Transfer Learning for Human-Object Interaction Detection","created":"2021-04-07","cited_by_count":79},{"id":"1806.11538","title":"Factorizable Net: An Efficient Subgraph-based Framework for Scene Graph Generation","created":"2018-06-29","cited_by_count":78},{"id":"1811.10696","title":"Attentive Relational Networks for Mapping Images to Scene Graphs","created":"2018-11-26","cited_by_count":73},{"id":"2108.09668","title":"Learning of Visual Relations: The Devil is in the Tails","created":"2021-08-22","cited_by_count":65},{"id":"2109.02227","title":"Learning to Generate Scene Graph from Natural Language Supervision","created":"2021-09-06","cited_by_count":64},{"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":"1910.07721","title":"Deep Contextual Attention for Human-Object Interaction Detection","created":"2019-10-17","cited_by_count":54},{"id":"2007.01072","title":"Scene Graph Reasoning for Visual Question Answering","created":"2020-07-02","cited_by_count":50},{"id":"2006.09623","title":"Learning Visual Commonsense for Robust Scene Graph Generation","created":"2020-06-17","cited_by_count":47},{"id":"2003.04262","title":"Cascaded Human-Object Interaction Recognition","created":"2020-03-09","cited_by_count":40},{"id":"2203.17251","title":"Continuous Scene Representations for Embodied AI","created":"2022-03-31","cited_by_count":39},{"id":"1707.09472","title":"Weakly-supervised learning of visual relations","created":"2017-07-29","cited_by_count":36},{"id":"2105.13994","title":"Linguistic Structures as Weak Supervision for Visual Scene Graph Generation","created":"2021-05-28","cited_by_count":29},{"id":"2104.14207","title":"Segmentation-grounded Scene Graph Generation","created":"2021-04-29","cited_by_count":25},{"id":"2202.10432","title":"Reasoning with Scene Graphs for Robot Planning under Partial Observability","created":"2022-02-21","cited_by_count":25},{"id":"1807.02136","title":"Detecting Visual Relationships Using Box Attention","created":"2018-07-05","cited_by_count":16},{"id":"2205.02958","title":"Scene Graph Expansion for Semantics-Guided Image Outpainting","created":"2022-05-05","cited_by_count":11}],"next_cursor":null}