Score: 1

HOI-R1: Exploring the Potential of Multimodal Large Language Models for Human-Object Interaction Detection

Published: October 7, 2025 | arXiv ID: 2510.05609v1

By: Junwen Chen, Peilin Xiong, Keiji Yanai

Potential Business Impact:

Lets computers understand actions between people and things.

Business Areas:
Image Recognition Data and Analytics, Software

Recent Human-object interaction detection (HOID) methods highly require prior knowledge from VLMs to enhance the interaction recognition capabilities. The training strategies and model architectures for connecting the knowledge from VLMs to the HOI instance representations from the object detector are challenging, and the whole framework is complex for further development or application. On the other hand, the inherent reasoning abilities of MLLMs on human-object interaction detection are under-explored. Inspired by the recent success of training MLLMs with reinforcement learning (RL) methods, we propose HOI-R1 and first explore the potential of the language model on the HOID task without any additional detection modules. We introduce an HOI reasoning process and HOID reward functions to solve the HOID task by pure text. The results on the HICO-DET dataset show that HOI-R1 achieves 2x the accuracy of the baseline with great generalization ability. The source code is available at https://github.com/cjw2021/HOI-R1.

Country of Origin
🇯🇵 Japan

Page Count
10 pages

Category
Computer Science:
CV and Pattern Recognition