GazeLLM: Multimodal LLMs incorporating Human Visual Attention

Video encoder A user With 1 st person vision & eye tracker Gaze focused video 1 st person viewFigure 1: GazeLLM achieves task descriptions of equal or superior quality to full-sized videos, despite using only one-tenth of the pixels around the user's gaze point.

Authors

Jun Rekimoto (ORCID: https://orcid.org/0000-0002-3629-2514)

Institutions

Sony Computer Science Laboratories (JP)
The University of Tokyo (JP)

Publication Details

Published: 2025-03-16
DOI: https://doi.org/10.1145/3745900.3746075
Citations: 1
Primary Topic: Gaze Tracking and Assistive Technology
Type: article
Field-Weighted Citation Impact: 1.94

Funders

Moonshot Research and Development Program

Controls

|||

ALL TIME

JAN

FEB

MAR

APR

MAY

JUN

JUL

AUG

SEP

OCT

article

GazeLLM: Multimodal LLMs incorporating Human Visual Attention

Jun Rekimoto

Mar 16, 2025

1 citations

Gaze Tracking and Assistive Technology

1.94

article

GazeLLM: Multimodal LLMs incorporating Human Visual Attention

Jun Rekimoto

March 16, 2025article en

1 citations

Abstract

Sony Computer Science Laboratories (JP), The University of Tokyo (JP)

Moonshot Research and Development Program

Openalex Percentile: Top 12%

Gaze Tracking and Assistive Technology

1.94

DOI Open Access PDF OpenAlex

AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

GazeLLM: Multimodal LLMs incorporating Human Visual Attention — Jun Rekimoto · (2025) | TGRS Research Map | TGRS