A depth-aware multimodal ERU framework with LLM data augmentation and a depth-aware decision module outperforms baselines for referent detection on two datasets.
Yourefit: Em- bodied reference understanding with language and gesture,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
A Multimodal Depth-Aware Method For Embodied Reference Understanding
A depth-aware multimodal ERU framework with LLM data augmentation and a depth-aware decision module outperforms baselines for referent detection on two datasets.