SemanticScanpath translates gaze scanpaths into semantic text to augment speech inputs for LLMs, enabling better resolution of ambiguous human-robot requests in situated scenarios.
The reliability of non-verbal cues for situated reference resolution and their interplay with language: implications for human robot interaction
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.HC 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
SemanticScanpath: Combining Gaze and Speech for Situated Human-Robot Interaction Using LLMs
SemanticScanpath translates gaze scanpaths into semantic text to augment speech inputs for LLMs, enabling better resolution of ambiguous human-robot requests in situated scenarios.