Gaze-to-text Generation: Beyond Categorical Decoding of Human Attention
2026-07-27 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors introduce a new way to understand what people want just by looking at where they look, turning their eye movements into sentences that describe their goals. Unlike past methods that limited the understanding to fixed categories, their approach generates open-ended natural language descriptions. They created Gazette, a system that uses advanced language models to translate eye movement patterns into goal explanations, helped by synthetic 'think-aloud' texts that explain attention patterns. This makes Gazette better at guessing human goals from gaze across many different tasks.
gaze decodingnatural language generationmultimodal large language modelsgaze scanpathsgoal-directed attentioninstruction tuningthink-aloud transcriptsgenerative learninghuman intention inference
Authors
Sounak Mondal, Dimitris Samaras, Gregory Zelinsky, Minh Hoai
Abstract
We introduce a novel learning problem: decoding gaze into natural language descriptions of human goals across diverse visual tasks. Unlike prior work, which frames gaze decoding as a discriminative task over predefined categories, we formulate it as a generative learning problem: training a model to produce free-form descriptions that capture the rich nuances and open-ended nature of human intentions beyond fixed labels. To this end, we introduce Gazette, the first gaze-to-text decoding framework. Based on multimodal large language models (MLLMs), Gazette learns to decode gaze scanpaths into natural language for goals that may extend beyond categorical labels and require articulation in natural language. To help Gazette filter out individual differences in gaze behavior and learn the goal-specific spatiotemporal dynamics crucial for generating accurate natural language goal descriptions, we propose a novel strategy that leverages the encyclopedic knowledge and reasoning abilities of a large language model to synthesize natural language explanations of goal-directed attentional behavior called think-aloud transcripts. Instruction tuning on these synthetic narratives allows Gazette to achieve state-of-the-art performance in gaze decoding across multiple tasks, demonstrating its generalizability and versatility, thereby enabling gaze to serve as a powerful, non-intrusive cue for inferring human goals and intentions in diverse scenarios.