{"list":"other","total":56,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"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":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1301.3781","title":"Efficient Estimation of Word Representations in Vector Space","created":"2013-01-16","cited_by_count":4375},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"1512.04150","title":"Learning Deep Features for Discriminative Localization","created":"2015-12-14","cited_by_count":2436},{"id":"2105.01601","title":"MLP-Mixer: An all-MLP Architecture for Vision","created":"2021-05-04","cited_by_count":1446},{"id":"1603.06937","title":"Stacked Hourglass Networks for Human Pose Estimation","created":"2016-03-22","cited_by_count":915},{"id":"1708.02002","title":"Focal Loss for Dense Object Detection","created":"2017-08-07","cited_by_count":752},{"id":"2202.11094","title":"GroupViT: Semantic Segmentation Emerges from Text Supervision","created":"2022-02-22","cited_by_count":531},{"id":"1707.06484","title":"Deep Layer Aggregation","created":"2017-07-20","cited_by_count":436},{"id":"2012.00759","title":"MaX-DeepLab: End-to-End Panoptic Segmentation with Mask Transformers","created":"2020-12-01","cited_by_count":355},{"id":"1612.00137","title":"RMPE: Regional Multi-person Pose Estimation","created":"2016-12-01","cited_by_count":340},{"id":"1702.05448","title":"Learning to Detect Human-Object Interactions","created":"2017-02-17","cited_by_count":240},{"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":"2007.11858","title":"Whole-Body Human Pose Estimation in the Wild","created":"2020-07-23","cited_by_count":178},{"id":"1808.07962","title":"Learning Human-Object Interactions by Graph Parsing Neural Networks","created":"2018-08-23","cited_by_count":176},{"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":"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":"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":"1808.10437","title":"iCAN: Instance-Centric Attention Network for Human-Object Interaction Detection","created":"2018-08-30","cited_by_count":127},{"id":"2203.13954","title":"GEN-VLKT: Simplify Association and Enhance Interaction Understanding for HOI Detection","created":"2022-03-26","cited_by_count":120},{"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":"2003.14023","title":"Learning Human-Object Interaction Detection using Interaction Points","created":"2020-03-31","cited_by_count":108},{"id":"2108.05077","title":"Mining the Benefits of Two-stage and One-stage HOI Detection","created":"2021-08-11","cited_by_count":103},{"id":"2104.06976","title":"Pose Recognition with Cascade Transformers","created":"2021-04-14","cited_by_count":99},{"id":"2103.05983","title":"Reformulating HOI Detection as Adaptive Set Prediction","created":"2021-03-10","cited_by_count":95},{"id":"2004.08154","title":"Detailed 2D-3D Joint Representation for Human-Object Interaction","created":"2020-04-17","cited_by_count":93},{"id":"2012.06060","title":"Spatially Conditioned Graphs for Detecting Human-Object Interactions","created":"2020-12-11","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":"2004.00945","title":"PaStaNet: Toward Human Activity Knowledge Engine","created":"2020-04-02","cited_by_count":80},{"id":"2007.08728","title":"Detecting Human-Object Interactions with Action Co-occurrence Priors","created":"2020-07-17","cited_by_count":72},{"id":"2104.05269","title":"Glance and Gaze: Inferring Action-aware Points for One-Stage Human-Object Interaction Detection","created":"2021-04-12","cited_by_count":58},{"id":"1910.07721","title":"Deep Contextual Attention for Human-Object Interaction Detection","created":"2019-10-17","cited_by_count":54},{"id":"2010.10001","title":"Contextual Heterogeneous Graph Network for Human-Object Interaction Detection","created":"2020-10-20","cited_by_count":50},{"id":"2203.10433","title":"End-to-End Human-Gaze-Target Detection with Transformers","created":"2022-03-20","cited_by_count":47},{"id":"2206.06291","title":"Exploring Structure-aware Transformer over Interaction Proposals for Human-Object Interaction Detection","created":"2022-06-13","cited_by_count":47},{"id":"2003.04262","title":"Cascaded Human-Object Interaction Recognition","created":"2020-03-09","cited_by_count":40},{"id":"2204.07718","title":"Interactiveness Field in Human-Object Interactions","created":"2022-04-16","cited_by_count":40},{"id":"2204.09290","title":"Human-Object Interaction Detection via Disentangled Transformer","created":"2022-04-20","cited_by_count":40},{"id":"2204.00746","title":"What to look at and where: Semantic and Spatial Refined Transformer for detecting human-object interactions","created":"2022-04-02","cited_by_count":35},{"id":"2203.14709","title":"MSTR: Multi-Scale Transformer for End-to-End Human-Object Interaction Detection","created":"2022-03-28","cited_by_count":34},{"id":"2105.02170","title":"Visual Relationship Detection Using Part-and-Sum Transformers with Composite Queries","created":"2021-05-05","cited_by_count":31},{"id":"1808.09796","title":"Interact as You Intend: Intention-Driven Human-Object Interaction Detection","created":"2018-08-29","cited_by_count":30},{"id":"2008.02918","title":"Polysemy Deciphering Network for Robust Human-Object Interaction Detection","created":"2020-08-07","cited_by_count":25},{"id":"2203.10537","title":"Iwin: Human-Object Interaction Detection via Transformer with Irregular Windows","created":"2022-03-20","cited_by_count":19},{"id":"2206.01908","title":"Video-based Human-Object Interaction Detection from Tubelet Tokens","created":"2022-06-04","cited_by_count":13},{"id":"2007.06925","title":"A Graph-based Interactive Reasoning for Human-Object Interaction Detection","created":"2020-07-14","cited_by_count":12},{"id":"1711.03636","title":"ANCHOR: logically-centralized security for Software-Defined Networks","created":"2017-11-09","cited_by_count":8}],"next_cursor":null}