{"total":30,"rows":[{"id":"2410.23904","title":"EZ-HOI: VLM Adaptation via Guided Prompt Learning for Zero-Shot HOI Detection","created":"2024-10-31","cited_by_count":28,"area":null},{"id":"2408.02484","title":"Exploring Conditional Multi-Modal Prompts for Zero-shot HOI Detection","created":"2024-08-05","cited_by_count":26,"area":null},{"id":"2503.23715","title":"HOIGen-1M: A Large-scale Dataset for Human-Object Interaction Video Generation","created":"2025-03-31","cited_by_count":26,"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":"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":"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":"2508.04546","title":"Hierarchical Event Memory for Accurate and Low-latency Online Video Temporal Grounding","created":"2025-08-06","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":"2403.07246","title":"Towards Zero-shot Human-Object Interaction Detection via Vision-Language Integration","created":"2024-03-12","cited_by_count":4,"area":null},{"id":"2512.09646","title":"VHOI: Controllable Video Generation of Human-Object Interactions from Sparse Trajectories via Motion Densification","created":"2025-12-10","cited_by_count":4,"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":"2506.14189","title":"Egocentric Human-Object Interaction Detection: A New Benchmark and Method","created":"2025-06-17","cited_by_count":3,"area":null},{"id":"2508.04943","title":"TRKT: Weakly Supervised Dynamic Scene Graph Generation with Temporal-enhanced Relation-aware Knowledge Transferring","created":"2025-08-07","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":"2509.23612","title":"InteractMove: Text-Controlled Human-Object Interaction Generation in 3D Scenes with Movable Objects","created":"2025-09-28","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":"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":"2507.17456","title":"Dynamic Scoring with Enhanced Semantics for Training-Free Human-Object Interaction Detection","created":"2025-07-23","cited_by_count":2,"area":null},{"id":"2508.18896","title":"DQEN: Dual Query Enhancement Network for DETR-based HOI Detection","created":"2025-08-26","cited_by_count":1,"area":null},{"id":"2511.18811","title":"Mitigating Long-Tail Bias in HOI Detection via Adaptive Diversity Cache","created":"2025-11-24","cited_by_count":1,"area":null},{"id":"2604.01586","title":"SHOE: Semantic HOI Open-Vocabulary Evaluation Metric","created":"2026-04-02","cited_by_count":1,"area":null},{"id":"2604.02071","title":"Mining Instance-Centric Vision-Language Contexts for Human-Object Interaction Detection","created":"2026-04-02","cited_by_count":1,"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":"2509.12784","title":"Contextualized Representation Learning for Effective Human-Object Interaction Detection","created":"2025-09-16","cited_by_count":0,"area":null},{"id":"2604.00507","title":"RegFormer: Transferable Relational Grounding for Efficient Weakly-Supervised Human-Object Interaction Detection","created":"2026-04-01","cited_by_count":0,"area":null},{"id":"2604.12923","title":"Pi-HOC: Pairwise 3D Human-Object Contact Estimation","created":"2026-04-14","cited_by_count":0,"area":null},{"id":"2604.13448","title":"A Study of Failure Modes in Two-Stage Human-Object Interaction Detection","created":"2026-04-15","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":"2605.04554","title":"InterMesh: Explicit Interaction-Aware End-to-End Multi-Person Human Mesh Recovery","created":"2026-05-06","cited_by_count":0,"area":null},{"id":"2609.05959","title":"FineHOI: Part-Aware Dense Representations for Zero-Shot Human-Object Interaction Detection","created":"2026-09-05","cited_by_count":0,"area":null}],"next_cursor":null}