{"total":73,"rows":[{"id":"2104.13682","title":"HOTR: End-to-End Human-Object Interaction Detection with Transformers","created":"2021-04-28","cited_by_count":183,"area":null},{"id":"2103.04503","title":"End-to-End Human Object Interaction Detection with HOI Transformer","created":"2021-03-08","cited_by_count":135,"area":null},{"id":"2309.15273","title":"DECO: Dense Estimation of 3D Human-Scene Contact In The Wild","created":"2023-09-26","cited_by_count":54,"area":null},{"id":"2312.08963","title":"LEMON: Learning 3D Human-Object Interaction Relation from 2D Images","created":"2023-12-14","cited_by_count":49,"area":null},{"id":"2103.07854","title":"Three Steps to Multimodal Trajectory Prediction: Modality Clustering, Classification and Synthesis","created":"2021-03-14","cited_by_count":46,"area":null},{"id":"2303.11726","title":"3D Human Mesh Estimation from Virtual Markers","created":"2023-03-21","cited_by_count":44,"area":null},{"id":"2209.08790","title":"D&D: Learning Human Dynamics from Dynamic Camera","created":"2022-09-19","cited_by_count":41,"area":null},{"id":"2303.03373","title":"Detecting Human-Object Contact in Images","created":"2023-03-06","cited_by_count":41,"area":null},{"id":"2204.07718","title":"Interactiveness Field in Human-Object Interactions","created":"2022-04-16","cited_by_count":40,"area":null},{"id":"2204.09290","title":"Human-Object Interaction Detection via Disentangled Transformer","created":"2022-04-20","cited_by_count":40,"area":null},{"id":"2203.14709","title":"MSTR: Multi-Scale Transformer for End-to-End Human-Object Interaction Detection","created":"2022-03-28","cited_by_count":34,"area":null},{"id":"2207.14192","title":"Mining Cross-Person Cues for Body-Part Interactiveness Learning in HOI Detection","created":"2022-07-28","cited_by_count":34,"area":null},{"id":"2105.02170","title":"Visual Relationship Detection Using Part-and-Sum Transformers with Composite Queries","created":"2021-05-05","cited_by_count":31,"area":null},{"id":"2301.04019","title":"FGAHOI: Fine-Grained Anchors for Human-Object Interaction Detection","created":"2023-01-08","cited_by_count":30,"area":null},{"id":"2202.06851","title":"HAKE: A Knowledge Engine Foundation for Human Activity Understanding","created":"2022-02-14","cited_by_count":28,"area":null},{"id":"2208.02567","title":"Constructing Balance from Imbalance for Long-tailed Image Recognition","created":"2022-08-04","cited_by_count":25,"area":null},{"id":"2404.06194","title":"Exploring the Potential of Large Foundation Models for Open-Vocabulary HOI Detection","created":"2024-04-09","cited_by_count":25,"area":null},{"id":"2204.04911","title":"Category-Aware Transformer Network for Better Human-Object Interaction Detection","created":"2022-04-11","cited_by_count":22,"area":null},{"id":"2504.17695","title":"PICO: Reconstructing 3D People In Contact with Objects","created":"2025-04-24","cited_by_count":22,"area":null},{"id":"2303.14005","title":"Category Query Learning for Human-Object Interaction Classification","created":"2023-03-24","cited_by_count":21,"area":null},{"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,"area":null},{"id":"2203.10537","title":"Iwin: Human-Object Interaction Detection via Transformer with Irregular Windows","created":"2022-03-20","cited_by_count":19,"area":null},{"id":"2304.00553","title":"From Isolated Islands to Pangea: Unifying Semantic Space for Human Action Understanding","created":"2023-04-02","cited_by_count":19,"area":null},{"id":"2110.07495","title":"Simple Baseline for Single Human Motion Forecasting","created":"2021-10-14","cited_by_count":18,"area":null},{"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,"area":null},{"id":"2112.07383","title":"Improving Human-Object Interaction Detection via Phrase Learning and Label Composition","created":"2021-12-14","cited_by_count":15,"area":null},{"id":"2204.11167","title":"RelViT: Concept-guided Vision Transformer for Visual Relational Reasoning","created":"2022-04-24","cited_by_count":15,"area":null},{"id":"2309.02423","title":"EgoPCA: A New Framework for Egocentric Hand-Object Interaction Understanding","created":"2023-09-05","cited_by_count":15,"area":null},{"id":"2311.01755","title":"Towards a Unified Transformer-based Framework for Scene Graph Generation and Human-object Interaction Detection","created":"2023-11-03","cited_by_count":15,"area":null},{"id":"2207.03714","title":"Jointly Harnessing Prior Structures and Temporal Consistency for Sign Language Video Generation","created":"2022-07-08","cited_by_count":14,"area":null},{"id":"2110.14994","title":"Skeleton-Based Mutually Assisted Interacted Object Localization and Human Action Recognition","created":"2021-10-28","cited_by_count":13,"area":null},{"id":"2503.15898","title":"Reconstructing In-the-Wild Open-Vocabulary Human-Object Interactions","created":"2025-03-20","cited_by_count":13,"area":null},{"id":"2311.15619","title":"Align before Adapt: Leveraging Entity-to-Region Alignments for Generalizable Video Action Recognition","created":"2023-11-27","cited_by_count":12,"area":null},{"id":"2212.02710","title":"Beyond Object Recognition: A New Benchmark towards Object Concept Learning","created":"2022-12-06","cited_by_count":11,"area":null},{"id":"2403.17709","title":"Groupwise Query Specialization and Quality-Aware Multi-Assignment for Transformer-based Visual Relationship Detection","created":"2024-03-26","cited_by_count":11,"area":null},{"id":"2202.09492","title":"Highlighting Object Category Immunity for the Generalization of Human-Object Interaction Detection","created":"2022-02-19","cited_by_count":9,"area":null},{"id":"2308.10158","title":"HODN: Disentangling Human-Object Feature for HOI Detection","created":"2023-08-20","cited_by_count":9,"area":null},{"id":"2108.00596","title":"GTNet:Guided Transformer Network for Detecting Human-Object Interactions","created":"2021-08-02","cited_by_count":8,"area":null},{"id":"2110.04603","title":"Learning Single/Multi-Attribute of Object with Symmetry and Group","created":"2021-10-09","cited_by_count":8,"area":null},{"id":"2112.06392","title":"The Overlooked Classifier in Human-Object Interaction Recognition","created":"2021-12-13","cited_by_count":8,"area":null},{"id":"2308.08370","title":"Agglomerative Transformer for Human-Object Interaction Detection","created":"2023-08-16","cited_by_count":8,"area":null},{"id":"2508.03207","title":"Open-Vocabulary HOI Detection with Interaction-aware Prompt and Concept Calibration","created":"2025-08-05","cited_by_count":8,"area":null},{"id":"2103.11313","title":"PGT: A Progressive Method for Training Models on Long Videos","created":"2021-03-21","cited_by_count":7,"area":null},{"id":"2211.07501","title":"Discovering A Variety of Objects in Spatio-Temporal Human-Object Interactions","created":"2022-11-14","cited_by_count":6,"area":null},{"id":"2412.19542","title":"Interacted Object Grounding in Spatio-Temporal Human-Object Interactions","created":"2024-12-27","cited_by_count":6,"area":null},{"id":"2112.07015","title":"Multi-Expert Human Action Recognition with Hierarchical Super-Class Learning","created":"2021-12-13","cited_by_count":5,"area":null},{"id":"2412.09920","title":"Precision-Enhanced Human-Object Contact Detection via Depth-Aware Perspective Interaction and Object Texture Restoration","created":"2024-12-13","cited_by_count":5,"area":null},{"id":"2403.15444","title":"A Survey of IMU Based Cross-Modal Transfer Learning in Human Activity Recognition","created":"2024-03-17","cited_by_count":4,"area":null},{"id":"2107.13083","title":"Is Object Detection Necessary for Human-Object Interaction Recognition?","created":"2021-07-27","cited_by_count":3,"area":null},{"id":"2111.11433","title":"Towards Tokenized Human Dynamics Representation","created":"2021-11-22","cited_by_count":3,"area":null},{"id":"2206.10146","title":"KE-RCNN: Unifying Knowledge based Reasoning into Part-level Attribute Parsing","created":"2022-06-21","cited_by_count":3,"area":null},{"id":"2207.05733","title":"A Skeleton-aware Graph Convolutional Network for Human-Object Interaction Detection","created":"2022-07-11","cited_by_count":3,"area":null},{"id":"2503.00414","title":"SGC-Net: Stratified Granular Comparison Network for Open-Vocabulary HOI Detection","created":"2025-03-01","cited_by_count":3,"area":null},{"id":"2202.11998","title":"Effective Actor-centric Human-object Interaction Detection","created":"2022-02-24","cited_by_count":2,"area":null},{"id":"2206.13577","title":"A View Independent Classification Framework for Yoga Postures","created":"2022-06-27","cited_by_count":2,"area":null},{"id":"2207.07742","title":"Human keypoint detection for close proximity human-robot interaction","created":"2022-07-15","cited_by_count":2,"area":null},{"id":"2207.12537","title":"Live Stream Temporally Embedded 3D Human Body Pose and Shape Estimation","created":"2022-07-25","cited_by_count":2,"area":null},{"id":"2304.10765","title":"BPJDet: Extended Object Representation for Generic Body-Part Joint Detection","created":"2023-04-21","cited_by_count":2,"area":null},{"id":"2507.16287","title":"Beyond Label Semantics: Language-Guided Action Anatomy for Few-shot Action Recognition","created":"2025-07-22","cited_by_count":2,"area":null},{"id":"2101.10292","title":"Transferable Interactiveness Knowledge for Human-Object Interaction Detection","created":"2021-01-25","cited_by_count":1,"area":null},{"id":"2211.10624","title":"A Unified Model for Video Understanding and Knowledge Embedding with Heterogeneous Knowledge Graph Dataset","created":"2022-11-19","cited_by_count":1,"area":null},{"id":"2306.14260","title":"HOKEM: Human and Object Keypoint-based Extension Module for Human-Object Interaction Detection","created":"2023-06-25","cited_by_count":1,"area":null},{"id":"2412.06146","title":"Homogeneous Dynamics Space for Heterogeneous Humans","created":"2024-12-09","cited_by_count":1,"area":null},{"id":"2507.01630","title":"Prompt Guidance and Human Proximal Perception for HOT Prediction with Regional Joint Loss","created":"2025-07-02","cited_by_count":1,"area":null},{"id":"2203.05676","title":"The Overlooked Classifier in Human-Object Interaction Recognition","created":"2022-03-10","cited_by_count":0,"area":null},{"id":"2307.10499","title":"Mining Conditional Part Semantics with Occluded Extrapolation for Human-Object Interaction Detection","created":"2023-07-19","cited_by_count":0,"area":null},{"id":"2309.09236","title":"Detection and Localization of Firearm Carriers in Complex Scenes for Improved Safety Measures","created":"2023-09-17","cited_by_count":0,"area":null},{"id":"2312.01713","title":"Disentangled Interaction Representation for One-Stage Human-Object Interaction Detection","created":"2023-12-04","cited_by_count":0,"area":null},{"id":"2405.17729","title":"Hierarchical Action Recognition: A Contrastive Video-Language Approach with Hierarchical Interactions","created":"2024-05-28","cited_by_count":0,"area":null},{"id":"2405.20084","title":"Estimating Human Poses Across Datasets: A Unified Skeleton and Multi-Teacher Distillation Approach","created":"2024-05-30","cited_by_count":0,"area":null},{"id":"2409.12980","title":"A New People-Object Interaction Dataset and NVS Benchmarks","created":"2024-09-03","cited_by_count":0,"area":null},{"id":"2504.19847","title":"Foundation Model-Driven Framework for Human-Object Interaction Prediction with Segmentation Mask Integration","created":"2025-04-28","cited_by_count":0,"area":null},{"id":"2508.09428","title":"What-Meets-Where: Unified Learning of Action and Contact Localization in Images","created":"2025-08-13","cited_by_count":0,"area":null}],"next_cursor":null}