{"total":80,"rows":[{"id":"2104.11181","title":"H2O: Two Hands Manipulating Objects for First Person Interaction Recognition","created":"2021-04-22","cited_by_count":254,"area":null},{"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":"2103.05399","title":"QPIC: Query-Based Pairwise Human-Object Interaction Detection with Image-Wide Contextual Information","created":"2021-03-09","cited_by_count":147,"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":"2203.13954","title":"GEN-VLKT: Simplify Association and Enhance Interaction Understanding for HOI Detection","created":"2022-03-26","cited_by_count":120,"area":null},{"id":"2108.05077","title":"Mining the Benefits of Two-stage and One-stage HOI Detection","created":"2021-08-11","cited_by_count":103,"area":null},{"id":"2103.05983","title":"Reformulating HOI Detection as Adaptive Set Prediction","created":"2021-03-10","cited_by_count":95,"area":null},{"id":"2103.08214","title":"Detecting Human-Object Interaction via Fabricated Compositional Learning","created":"2021-03-15","cited_by_count":79,"area":null},{"id":"2104.02867","title":"Affordance Transfer Learning for Human-Object Interaction Detection","created":"2021-04-07","cited_by_count":79,"area":null},{"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,"area":null},{"id":"2104.11536","title":"Recent Advances in Monocular 2D and 3D Human Pose Estimation: A Deep Learning Perspective","created":"2021-04-23","cited_by_count":50,"area":null},{"id":"2304.08114","title":"ViPLO: Vision Transformer based Pose-Conditioned Self-Loop Graph for Human-Object Interaction Detection","created":"2023-04-17","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":"2309.03696","title":"Efficient Adaptive Human-Object Interaction Detection with Concept-guided Memory","created":"2023-09-07","cited_by_count":38,"area":null},{"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,"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":"2312.12664","title":"UnionDet: Union-Level Detector Towards Real-Time Human-Object Interaction Detection","created":"2023-12-19","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":"2112.08647","title":"QAHOI: Query-Based Anchors for Human-Object Interaction Detection","created":"2021-12-16","cited_by_count":28,"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":"2406.07221","title":"Open-World Human-Object Interaction Detection via Multi-modal Prompts","created":"2024-06-11","cited_by_count":28,"area":null},{"id":"2311.09817","title":"Neural-Logic Human-Object Interaction Detection","created":"2023-11-16","cited_by_count":25,"area":null},{"id":"2202.00259","title":"Detecting Human-Object Interactions with Object-Guided Cross-Modal Calibrated Semantics","created":"2022-02-01","cited_by_count":22,"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":"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":"2108.08363","title":"Social Fabric: Tubelet Compositions for Video Relation Detection","created":"2021-08-18","cited_by_count":18,"area":null},{"id":"2207.09425","title":"Geometric Features Informed Multi-person Human-object Interaction Recognition in Videos","created":"2022-07-19","cited_by_count":17,"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":"2206.01908","title":"Video-based Human-Object Interaction Detection from Tubelet Tokens","created":"2022-06-04","cited_by_count":13,"area":null},{"id":"2303.08998","title":"Unified Visual Relationship Detection with Vision and Language Models","created":"2023-03-16","cited_by_count":13,"area":null},{"id":"2307.13529","title":"Re-mine, Learn and Reason: Exploring the Cross-modal Semantic Correlations for Language-guided HOI detection","created":"2023-07-25","cited_by_count":13,"area":null},{"id":"2207.05293","title":"Towards Hard-Positive Query Mining for DETR-based Human-Object Interaction Detection","created":"2022-07-12","cited_by_count":12,"area":null},{"id":"2109.04047","title":"ACP++: Action Co-occurrence Priors for Human-Object Interaction Detection","created":"2021-09-09","cited_by_count":11,"area":null},{"id":"2303.01313","title":"Weakly-supervised HOI Detection via Prior-guided Bi-level Representation Learning","created":"2023-03-02","cited_by_count":11,"area":null},{"id":"2207.02400","title":"Chairs Can be Stood on: Overcoming Object Bias in Human-Object Interaction Detection","created":"2022-07-06","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":"2110.03562","title":"Weakly Supervised Human-Object Interaction Detection in Video via Contrastive Spatiotemporal Regions","created":"2021-10-07","cited_by_count":8,"area":null},{"id":"2207.01869","title":"Distance Matters in Human-Object Interaction Detection","created":"2022-07-05","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":"2105.11168","title":"Human-centric Relation Segmentation: Dataset and Solution","created":"2021-05-24","cited_by_count":7,"area":null},{"id":"2201.04906","title":"Hand-Object Interaction Reasoning","created":"2022-01-13","cited_by_count":7,"area":null},{"id":"2407.20545","title":"StackFLOW: Monocular Human-Object Reconstruction by Stacked Normalizing Flow with Offset","created":"2024-07-30","cited_by_count":5,"area":null},{"id":"2408.10641","title":"A Review of Human-Object Interaction Detection","created":"2024-08-20","cited_by_count":5,"area":null},{"id":"2503.18134","title":"An Image-like Diffusion Method for Human-Object Interaction Detection","created":"2025-03-23","cited_by_count":5,"area":null},{"id":"2510.18357","title":"Learning Human-Object Interaction as Groups","created":"2025-10-21","cited_by_count":5,"area":null},{"id":"2408.07430","title":"UAHOI: Uncertainty-aware Robust Interaction Learning for HOI Detection","created":"2024-08-14","cited_by_count":4,"area":null},{"id":"2105.03089","title":"Human Object Interaction Detection using Two-Direction Spatial Enhancement and Exclusive Object Prior","created":"2021-05-07","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":"2301.07666","title":"DDS: Decoupled Dynamic Scene-Graph Generation Network","created":"2023-01-18","cited_by_count":3,"area":null},{"id":"2304.14104","title":"Learning Human-Human Interactions in Images from Weak Textual Supervision","created":"2023-04-27","cited_by_count":3,"area":null},{"id":"2506.03440","title":"Geometric Visual Fusion Graph Neural Networks for Multi-Person Human-Object Interaction Recognition in Videos","created":"2025-06-03","cited_by_count":3,"area":null},{"id":"2506.14189","title":"Egocentric Human-Object Interaction Detection: A New Benchmark and Method","created":"2025-06-17","cited_by_count":3,"area":null},{"id":"2507.09111","title":"RoHOI: Robustness Benchmark for Human-Object Interaction Detection","created":"2025-07-12","cited_by_count":3,"area":null},{"id":"2509.00760","title":"No More Sibling Rivalry: Debiasing Human-Object Interaction Detection","created":"2025-08-31","cited_by_count":3,"area":null},{"id":"2510.07828","title":"MMHOI: Modeling Complex 3D Multi-Human Multi-Object Interactions","created":"2025-10-09","cited_by_count":3,"area":null},{"id":"2201.02396","title":"Detecting Human-to-Human-or-Object (H2O) Interactions with DIABOLO","created":"2022-01-07","cited_by_count":2,"area":null},{"id":"2202.11998","title":"Effective Actor-centric Human-object Interaction Detection","created":"2022-02-24","cited_by_count":2,"area":null},{"id":"2301.03510","title":"Parallel Reasoning Network for Human-Object Interaction Detection","created":"2023-01-09","cited_by_count":2,"area":null},{"id":"2308.05961","title":"Compositional Learning in Transformer-Based Human-Object Interaction Detection","created":"2023-08-11","cited_by_count":2,"area":null},{"id":"2406.18691","title":"Geometric Features Enhanced Human-Object Interaction Detection","created":"2024-06-26","cited_by_count":2,"area":null},{"id":"2408.08305","title":"Towards Flexible Visual Relationship Segmentation","created":"2024-08-15","cited_by_count":2,"area":null},{"id":"2603.27500","title":"Streamlined Open-Vocabulary Human-Object Interaction Detection","created":"2026-03-29","cited_by_count":2,"area":null},{"id":"2104.15015","title":"RR-Net: Injecting Interactive Semantics in Human-Object Interaction Detection","created":"2021-04-30","cited_by_count":1,"area":null},{"id":"2303.04253","title":"TMHOI: Translational Model for Human-Object Interaction Detection","created":"2023-03-07","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":"2609.23431","title":"HOIBlender: Blending Lightweight Detection with Vision-Language Priors for Efficient Human-Object Interaction Detection","created":"2026-09-20","cited_by_count":1,"area":null},{"id":"2207.07979","title":"Knowledge Guided Bidirectional Attention Network for Human-Object Interaction Detection","created":"2022-07-16","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":"2312.01713","title":"Disentangled Interaction Representation for One-Stage Human-Object Interaction Detection","created":"2023-12-04","cited_by_count":0,"area":null},{"id":"2403.01840","title":"FreeA: Human-object Interaction Detection using Free Annotation Labels","created":"2024-03-04","cited_by_count":0,"area":null},{"id":"2408.07018","title":"Efficient Human-Object-Interaction (EHOI) Detection via Interaction Label Coding and Conditional Decision","created":"2024-08-13","cited_by_count":0,"area":null},{"id":"2506.18021","title":"On the Robustness of Human-Object Interaction Detection against Distribution Shift","created":"2025-06-22","cited_by_count":0,"area":null},{"id":"2511.03666","title":"Part-Aware Bottom-Up Group Reasoning for Fine-Grained Social Interaction Detection","created":"2025-11-05","cited_by_count":0,"area":null}],"next_cursor":null}