Visual prompting converts eye-tracking data into images that let MLLMs perform human activity recognition in a token-efficient way across public datasets.
Gaze2prompt: Turning eye-tracking data into visual prompts for multimodal llms,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.HC 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Evaluating Visual Prompts with Eye-Tracking Data for MLLM-Based Human Activity Recognition
Visual prompting converts eye-tracking data into images that let MLLMs perform human activity recognition in a token-efficient way across public datasets.