{"total":22,"rows":[{"id":"2504.07958","title":"Detect Anything 3D in the Wild","created":"2025-04-10","cited_by_count":33,"area":null},{"id":"2407.12435","title":"F-HOI: Toward Fine-grained Semantic-Aligned 3D Human-Object Interactions","created":"2024-07-17","cited_by_count":24,"area":null},{"id":"2507.15542","title":"HOLa: Zero-Shot HOI Detection with Low-Rank Decomposed VLM Feature Adaptation","created":"2025-07-21","cited_by_count":12,"area":null},{"id":"2511.15046","title":"UniHOI: Unified Human-Object Interaction Understanding via Unified Token Space","created":"2025-11-19","cited_by_count":10,"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":"2503.18134","title":"An Image-like Diffusion Method for Human-Object Interaction Detection","created":"2025-03-23","cited_by_count":5,"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":"2509.00760","title":"No More Sibling Rivalry: Debiasing Human-Object Interaction Detection","created":"2025-08-31","cited_by_count":3,"area":null},{"id":"2510.25094","title":"Visual Diversity and Region-aware Prompt Learning for Zero-shot HOI Detection","created":"2025-10-29","cited_by_count":3,"area":null},{"id":"2604.03315","title":"StoryBlender: Inter-Shot Consistent and Editable 3D Storyboard with Spatial-temporal Dynamics","created":"2026-04-01","cited_by_count":3,"area":null},{"id":"2412.08506","title":"Orchestrating the Symphony of Prompt Distribution Learning for Human-Object Interaction Detection","created":"2024-12-11","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":"2604.10397","title":"Rethinking Video Human-Object Interaction: Set Prediction over Time for Unified Detection and Anticipation","created":"2026-04-12","cited_by_count":2,"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":"2501.16724","title":"B-RIGHT: Benchmark Re-evaluation for Integrity in Generalized Human-Object Interaction Testing","created":"2025-01-28","cited_by_count":0,"area":null},{"id":"2501.17171","title":"Separated Inter/Intra-Modal Fusion Prompts for Compositional Zero-Shot Learning","created":"2025-01-22","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":"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},{"id":"2509.12554","title":"Multimodal Graph Network Modeling for Human-Object Interaction Detection with PDE Graph Diffusion","created":"2025-09-16","cited_by_count":0,"area":null},{"id":"2509.26004","title":"Learning Egocentric In-Hand Object Segmentation through Weak Supervision from Human Narrations","created":"2025-09-30","cited_by_count":0,"area":null},{"id":"2604.14069","title":"Towards Unconstrained Human-Object Interaction","created":"2026-04-15","cited_by_count":0,"area":null},{"id":"2609.12155","title":"Single-Query Person-Centric Bimanual Hand-Object Interaction Detection","created":"2026-09-10","cited_by_count":0,"area":null}],"next_cursor":null}