Showing cs.CVShow all
2 papers · 1 filter
cs.CV2025
Beyond Object Categories: Multi-Attribute Reference Understanding for Visual Grounding
Hao Guo, Jianfei Zhu, Wei Fan +2
Referring expression comprehension (REC) aims at achieving object localization based on natural language descriptions. However, existing REC approaches are constrained by object ca…
cs.CV2024
AD-DINO: Attention-Dynamic DINO for Distance-Aware Embodied Reference Understanding
Hao Guo, Wei Fan, Baichun Wei +4
Embodied reference understanding is crucial for intelligent agents to predict referents based on human intention through gesture signals and language descriptions. This paper intro…