{"list":"other","total":56,"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":"1609.02907","title":"Semi-Supervised Classification with Graph Convolutional Networks","created":"2016-09-09","cited_by_count":11361},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"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":"1602.07332","title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","created":"2016-02-23","cited_by_count":2656},{"id":"1606.09282","title":"Learning without Forgetting","created":"2016-06-29","cited_by_count":2496},{"id":"1711.07971","title":"Non-local Neural Networks","created":"2017-11-21","cited_by_count":2293},{"id":"1612.06890","title":"CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning","created":"2016-12-20","cited_by_count":1457},{"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":"1808.00191","title":"Graph R-CNN for Scene Graph Generation","created":"2018-08-01","cited_by_count":298},{"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":"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":"1808.07962","title":"Learning Human-Object Interactions by Graph Parsing Neural Networks","created":"2018-08-23","cited_by_count":176},{"id":"1707.09700","title":"Scene Graph Generation from Objects, Phrases and Region Captions","created":"2017-07-31","cited_by_count":154},{"id":"1912.12898","title":"PPDM: Parallel Point Detection and Matching for Real-time Human-Object Interaction Detection","created":"2019-12-30","cited_by_count":143},{"id":"1603.06318","title":"Harnessing Deep Neural Networks with Logic Rules","created":"2016-03-21","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":"1808.10437","title":"iCAN: Instance-Centric Attention Network for Human-Object Interaction Detection","created":"2018-08-30","cited_by_count":127},{"id":"2008.11714","title":"DRG: Dual Relation Graph for Human-Object Interaction Detection","created":"2020-08-26","cited_by_count":117},{"id":"2003.05541","title":"VSGNet: Spatial Attention Network for Detecting Human Object Interactions Using Graph Convolutions","created":"2020-03-11","cited_by_count":115},{"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":"2007.08844","title":"Distribution Aligning Refinery of Pseudo-label for Imbalanced Semi-supervised Learning","created":"2020-07-17","cited_by_count":105},{"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":"1909.08453","title":"Pose-aware Multi-level Feature Network for Human Object Interaction Detection","created":"2019-09-18","cited_by_count":88},{"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":"2007.08728","title":"Detecting Human-Object Interactions with Action Co-occurrence Priors","created":"2020-07-17","cited_by_count":72},{"id":"1806.06157","title":"Object Level Visual Reasoning in Videos","created":"2018-06-16","cited_by_count":67},{"id":"1707.09423","title":"Visual Relationship Detection with Internal and External Linguistic Knowledge Distillation","created":"2017-07-28","cited_by_count":61},{"id":"1910.07721","title":"Deep Contextual Attention for Human-Object Interaction Detection","created":"2019-10-17","cited_by_count":54},{"id":"1904.03181","title":"Detecting Human-Object Interactions via Functional Generalization","created":"2019-04-05","cited_by_count":53},{"id":"2010.10001","title":"Contextual Heterogeneous Graph Network for Human-Object Interaction Detection","created":"2020-10-20","cited_by_count":50},{"id":"1811.06410","title":"LinkNet: Relational Embedding for Scene Graph","created":"2018-11-15","cited_by_count":45},{"id":"1807.04979","title":"Zoom-Net: Mining Deep Feature Interactions for Visual Relationship Recognition","created":"2018-07-13","cited_by_count":41},{"id":"1903.05942","title":"Dense Relational Captioning: Triple-Stream Networks for Relationship-Based Captioning","created":"2019-03-14","cited_by_count":35},{"id":"1808.09796","title":"Interact as You Intend: Intention-Driven Human-Object Interaction Detection","created":"2018-08-29","cited_by_count":30},{"id":"1909.02201","title":"Image Captioning with Very Scarce Supervised Data: Adversarial Semi-Supervised Learning Approach","created":"2019-09-05","cited_by_count":30},{"id":"1905.01595","title":"On Exploring Undetermined Relationships for Visual Relationship Detection","created":"2019-05-05","cited_by_count":26},{"id":"1703.06246","title":"Towards Context-aware Interaction Recognition","created":"2017-03-18","cited_by_count":20},{"id":"1802.04962","title":"Disjoint Multi-task Learning between Heterogeneous Human-centric Tasks","created":"2018-02-14","cited_by_count":16},{"id":"2104.05965","title":"Dealing with Missing Modalities in the Visual Question Answer-Difference Prediction Task through Knowledge Distillation","created":"2021-04-13","cited_by_count":14},{"id":"1808.00171","title":"Shuffle-Then-Assemble: Learning Object-Agnostic Visual Relationship Features","created":"2018-08-01","cited_by_count":11},{"id":"2010.03855","title":"Dense Relational Image Captioning via Multi-task Triple-Stream Networks","created":"2020-10-08","cited_by_count":11},{"id":"1702.07191","title":"ViP-CNN: Visual Phrase Guided Convolutional Neural Network","created":"2017-02-23","cited_by_count":8},{"id":"1712.10151","title":"Significance of Softmax-based Features in Comparison to Distance Metric Learning-based Features","created":"2017-12-29","cited_by_count":8},{"id":"1805.11737","title":"Superpixel-enhanced Pairwise Conditional Random Field for Semantic Segmentation","created":"2018-05-29","cited_by_count":4},{"id":"1811.07123","title":"Explicit Spatiotemporal Joint Relation Learning for Tracking Human Pose","created":"2018-11-17","cited_by_count":3}],"next_cursor":null}