English

Beyond Object Categories: Multi-Attribute Reference Understanding for Visual Grounding

Computer Vision and Pattern Recognition 2025-03-26 v1 Human-Computer Interaction

Abstract

Referring expression comprehension (REC) aims at achieving object localization based on natural language descriptions. However, existing REC approaches are constrained by object category descriptions and single-attribute intention descriptions, hindering their application in real-world scenarios. In natural human-robot interactions, users often express their desires through individual states and intentions, accompanied by guiding gestures, rather than detailed object descriptions. To address this challenge, we propose Multi-ref EC, a novel task framework that integrates state descriptions, derived intentions, and embodied gestures to locate target objects. We introduce the State-Intention-Gesture Attributes Reference (SIGAR) dataset, which combines state and intention expressions with embodied references. Through extensive experiments with various baseline models on SIGAR, we demonstrate that properly ordered multi-attribute references contribute to improved localization performance, revealing that single-attribute reference is insufficient for natural human-robot interaction scenarios. Our findings underscore the importance of multi-attribute reference expressions in advancing visual-language understanding.

Keywords

Cite

@article{arxiv.2503.19240,
  title  = {Beyond Object Categories: Multi-Attribute Reference Understanding for Visual Grounding},
  author = {Hao Guo and Jianfei Zhu and Wei Fan and Chunzhi Yi and Feng Jiang},
  journal= {arXiv preprint arXiv:2503.19240},
  year   = {2025}
}
R2 v1 2026-06-28T22:33:12.333Z