{"list":"other","total":86,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"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":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"1301.3781","title":"Efficient Estimation of Word Representations in Vector Space","created":"2013-01-16","cited_by_count":4375},{"id":"2102.05918","title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision","created":"2021-02-11","cited_by_count":3864},{"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":"2107.07651","title":"Align before Fuse: Vision and Language Representation Learning with Momentum Distillation","created":"2021-07-16","cited_by_count":1619},{"id":"1904.05866","title":"Expressive Body Capture: 3D Hands, Face, and Body from a Single Image","created":"2019-04-11","cited_by_count":1612},{"id":"1907.01341","title":"Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer","created":"2019-07-02","cited_by_count":1495},{"id":"1902.09630","title":"Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression","created":"2019-02-25","cited_by_count":1368},{"id":"2205.01917","title":"CoCa: Contrastive Captioners are Image-Text Foundation Models","created":"2022-05-04","cited_by_count":1274},{"id":"2112.03857","title":"Grounded Language-Image Pre-training","created":"2021-12-07","cited_by_count":1156},{"id":"2103.03206","title":"Perceiver: General Perception with Iterative Attention","created":"2021-03-04","cited_by_count":1104},{"id":"1611.08050","title":"Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields","created":"2016-11-24","cited_by_count":1064},{"id":"1603.09382","title":"Deep Networks with Stochastic Depth","created":"2016-03-30","cited_by_count":979},{"id":"2104.13921","title":"Open-vocabulary Object Detection via Vision and Language Knowledge Distillation","created":"2021-04-28","cited_by_count":906},{"id":"2209.06794","title":"PaLI: A Jointly-Scaled Multilingual Language-Image Model","created":"2022-09-14","cited_by_count":766},{"id":"1708.02002","title":"Focal Loss for Dense Object Detection","created":"2017-08-07","cited_by_count":752},{"id":"2112.09106","title":"RegionCLIP: Region-based Language-Image Pretraining","created":"2021-12-16","cited_by_count":616},{"id":"2111.07991","title":"LiT: Zero-Shot Transfer with Locked-image text Tuning","created":"2021-11-15","cited_by_count":577},{"id":"2112.01518","title":"DenseCLIP: Language-Guided Dense Prediction with Context-Aware Prompting","created":"2021-12-02","cited_by_count":532},{"id":"1701.02426","title":"Scene Graph Generation by Iterative Message Passing","created":"2017-01-10","cited_by_count":462},{"id":"2011.10678","title":"Open-Vocabulary Object Detection Using Captions","created":"2020-11-20","cited_by_count":427},{"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":"2205.06230","title":"Simple Open-Vocabulary Object Detection with Vision Transformers","created":"2022-05-12","cited_by_count":305},{"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":"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":"2109.11797","title":"CPT: Colorful Prompt Tuning for Pre-trained Vision-Language Models","created":"2021-09-24","cited_by_count":183},{"id":"1808.07962","title":"Learning Human-Object Interactions by Graph Parsing Neural Networks","created":"2018-08-23","cited_by_count":176},{"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":"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":"2104.00308","title":"Bipartite Graph Network with Adaptive Message Passing for Unbiased Scene Graph Generation","created":"2021-04-01","cited_by_count":137},{"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":"2103.07461","title":"Probabilistic two-stage detection","created":"2021-03-12","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":"2102.13086","title":"Simple multi-dataset detection","created":"2021-02-25","cited_by_count":127},{"id":"1912.06704","title":"Hierarchical Deep Stereo Matching on High-resolution Images","created":"2019-12-13","cited_by_count":126},{"id":"2112.13762","title":"MSeg: A Composite Dataset for Multi-domain Semantic Segmentation","created":"2021-12-27","cited_by_count":122},{"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":"2207.08954","title":"Exploiting Unlabeled Data with Vision and Language Models for Object Detection","created":"2022-07-18","cited_by_count":97},{"id":"2201.11460","title":"RelTR: Relation Transformer for Scene Graph Generation","created":"2022-01-27","cited_by_count":96},{"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":"1904.04402","title":"Towards Universal Object Detection by Domain Attention","created":"2019-04-09","cited_by_count":89},{"id":"1909.08453","title":"Pose-aware Multi-level Feature Network for Human Object Interaction Detection","created":"2019-09-18","cited_by_count":88},{"id":"2001.02314","title":"Bridging Knowledge Graphs to Generate Scene Graphs","created":"2020-01-07","cited_by_count":86},{"id":"2010.16219","title":"HOI Analysis: Integrating and Decomposing Human-Object Interaction","created":"2020-10-30","cited_by_count":81},{"id":"2104.02867","title":"Affordance Transfer Learning for Human-Object Interaction Detection","created":"2021-04-07","cited_by_count":79},{"id":"2009.00893","title":"PCPL: Predicate-Correlation Perception Learning for Unbiased Scene Graph Generation","created":"2020-09-02","cited_by_count":75},{"id":"2007.08728","title":"Detecting Human-Object Interactions with Action Co-occurrence Priors","created":"2020-07-17","cited_by_count":72},{"id":"2107.02112","title":"Recovering the Unbiased Scene Graphs from the Biased Ones","created":"2021-07-05","cited_by_count":71},{"id":"2008.06614","title":"Object Detection with a Unified Label Space from Multiple Datasets","created":"2020-08-15","cited_by_count":65},{"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":"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":"2110.11403","title":"SCENIC: A JAX Library for Computer Vision Research and Beyond","created":"2021-10-18","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":"2209.01814","title":"RLIP: Relational Language-Image Pre-training for Human-Object Interaction Detection","created":"2022-09-05","cited_by_count":55},{"id":"2010.10001","title":"Contextual Heterogeneous Graph Network for Human-Object Interaction Detection","created":"2020-10-20","cited_by_count":50},{"id":"2204.07718","title":"Interactiveness Field in Human-Object Interactions","created":"2022-04-16","cited_by_count":40},{"id":"2207.14192","title":"Mining Cross-Person Cues for Body-Part Interactiveness Learning in HOI Detection","created":"2022-07-28","cited_by_count":34},{"id":"2010.01005","title":"DIRV: Dense Interaction Region Voting for End-to-End Human-Object Interaction Detection","created":"2020-10-02","cited_by_count":31},{"id":"2205.11169","title":"PEVL: Position-enhanced Pre-training and Prompt Tuning for Vision-language Models","created":"2022-05-23","cited_by_count":30},{"id":"2004.00436","title":"Exploring Long Tail Visual Relationship Recognition with Large Vocabulary","created":"2020-03-25","cited_by_count":16},{"id":"2204.04836","title":"Consistency Learning via Decoding Path Augmentation for Transformers in Human Object Interaction Detection","created":"2022-04-11","cited_by_count":16},{"id":"2207.05293","title":"Towards Hard-Positive Query Mining for DETR-based Human-Object Interaction Detection","created":"2022-07-12","cited_by_count":12}],"next_cursor":null}