{"total":46,"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":"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":"2103.08214","title":"Detecting Human-Object Interaction via Fabricated Compositional Learning","created":"2021-03-15","cited_by_count":79,"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":"2311.03799","title":"Detecting Any Human-Object Interaction Relationship: Universal HOI Detector with Spatial Prompt Learning on Foundation Models","created":"2023-11-07","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":"2406.07221","title":"Open-World Human-Object Interaction Detection via Multi-modal Prompts","created":"2024-06-11","cited_by_count":28,"area":null},{"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":"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":"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":"2303.14005","title":"Category Query Learning for Human-Object Interaction Classification","created":"2023-03-24","cited_by_count":21,"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":"2304.05387","title":"MOST: Multiple Object localization with Self-supervised Transformers for object discovery","created":"2023-04-11","cited_by_count":17,"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":"2203.14272","title":"Discovering Human-Object Interaction Concepts via Self-Compositional Learning","created":"2022-03-27","cited_by_count":15,"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":"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":"2109.04047","title":"ACP++: Action Co-occurrence Priors for Human-Object Interaction Detection","created":"2021-09-09","cited_by_count":11,"area":null},{"id":"2408.05974","title":"Unseen No More: Unlocking the Potential of CLIP for Generative Zero-shot HOI Detection","created":"2024-08-12","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":"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":"2112.06392","title":"The Overlooked Classifier in Human-Object Interaction Recognition","created":"2021-12-13","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":"2407.21438","title":"A Plug-and-Play Method for Rare Human-Object Interactions Detection by Bridging Domain Gap","created":"2024-07-31","cited_by_count":6,"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":"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":"2509.00760","title":"No More Sibling Rivalry: Debiasing Human-Object Interaction Detection","created":"2025-08-31","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":"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":"2408.08305","title":"Towards Flexible Visual Relationship Segmentation","created":"2024-08-15","cited_by_count":2,"area":null},{"id":"2112.09448","title":"Distillation of Human-Object Interaction Contexts for Action Recognition","created":"2021-12-17","cited_by_count":1,"area":null},{"id":"2108.05539","title":"Put the Bear on the Chair! Intelligent Robot Interaction with Previously Unseen Chairs via Robot Imagination","created":"2021-08-12","cited_by_count":0,"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":"2207.07979","title":"Knowledge Guided Bidirectional Attention Network for Human-Object Interaction Detection","created":"2022-07-16","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":"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":"2507.12628","title":"Funnel-HOI: Top-Down Perception for Zero-Shot HOI Detection","created":"2025-07-16","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}