ITE Technical Group Submission System
Conference Paper's Information
Online Proceedings
[Sign in]
 Go Top Page Go Previous   [Japanese] / [English] 

Paper Abstract and Keywords
Presentation 2026-02-17 09:40
Inference of Cognitive States through Large Language Models and Gaze Information -- An Examination of Mind-Reading Technology --
Nayuta Tada (Kindai Univ.), Fumika Nakanishi, Minori Yamataka (ARIC, DENSO CORP.), Takeshi Kohama (Kindai Univ.)
Abstract (in Japanese) (See Japanese page) 
(in English) This study aimed to develop gaze-based mind-reading technology by extending BLIP-2, a deep learning model for image-to-text generation, to integrate gaze information into its attention mechanism. The training data consisted of gaze data measured while participants observed images after being presented with questions. Additionally, to reduce data collection costs, we created a subjective evaluation dataset in which humans assessed the instruction content of existing data and attempted to use this dataset for training purposes. The results showed that the model trained on the measured data achieved favorable scores for the evaluation metrics. Furthermore, we confirmed that varying the input gaze data for a given image alters the generated text. Conversely, training with the subjective evaluation dataset led to early overfitting, highlighting the remaining challenges in the data construction method. The prediction accuracy obtained with the measured data suggests that gaze information contributes to the proposed model's text generation, indicating the potential for developing gaze-based mind-reading technology.
Keyword (in Japanese) (See Japanese page) 
(in English) Large language model / Gaze information / Text generation / Mind-reading / / / /  
Reference Info. ITE Tech. Rep., vol. 50, no. 4, HI2026-1, pp. 1-5, Feb. 2026.
Paper # HI2026-1 
Date of Issue 2026-02-10 (HI) 
ISSN Online edition: ISSN 2424-1970
Download PDF

Conference Information
Committee IEICE-HIP HI VRPSY ASJ-H  
Conference Date 2026-02-17 - 2026-02-18 
Place (in Japanese) (See Japanese page) 
Place (in English)  
Topics (in Japanese) (See Japanese page) 
Topics (in English)  
Paper Information
Registration To HI 
Conference Code 2026-02-HIP-HI-VRPSY-H 
Language Japanese 
Title (in Japanese) (See Japanese page) 
Sub Title (in Japanese) (See Japanese page) 
Title (in English) Inference of Cognitive States through Large Language Models and Gaze Information 
Sub Title (in English) An Examination of Mind-Reading Technology 
Keyword(1) Large language model  
Keyword(2) Gaze information  
Keyword(3) Text generation  
Keyword(4) Mind-reading  
Keyword(5)  
Keyword(6)  
Keyword(7)  
Keyword(8)  
1st Author's Name Nayuta Tada  
1st Author's Affiliation Kindai University (Kindai Univ.)
2nd Author's Name Fumika Nakanishi  
2nd Author's Affiliation Advanced Research and Innovation Center, DENSO CORPORATION (ARIC, DENSO CORP.)
3rd Author's Name Minori Yamataka  
3rd Author's Affiliation Advanced Research and Innovation Center, DENSO CORPORATION (ARIC, DENSO CORP.)
4th Author's Name Takeshi Kohama  
4th Author's Affiliation Kindai University (Kindai Univ.)
5th Author's Name  
5th Author's Affiliation ()
6th Author's Name  
6th Author's Affiliation ()
7th Author's Name  
7th Author's Affiliation ()
8th Author's Name  
8th Author's Affiliation ()
9th Author's Name  
9th Author's Affiliation ()
10th Author's Name  
10th Author's Affiliation ()
11th Author's Name  
11th Author's Affiliation ()
12th Author's Name  
12th Author's Affiliation ()
13th Author's Name  
13th Author's Affiliation ()
14th Author's Name  
14th Author's Affiliation ()
15th Author's Name  
15th Author's Affiliation ()
16th Author's Name  
16th Author's Affiliation ()
17th Author's Name  
17th Author's Affiliation ()
18th Author's Name  
18th Author's Affiliation ()
19th Author's Name  
19th Author's Affiliation ()
20th Author's Name  
20th Author's Affiliation ()
21st Author's Name  
21st Author's Affiliation ()
22nd Author's Name  
22nd Author's Affiliation ()
23rd Author's Name  
23rd Author's Affiliation ()
24th Author's Name  
24th Author's Affiliation ()
25th Author's Name  
25th Author's Affiliation ()
26th Author's Name / /
26th Author's Affiliation ()
()
27th Author's Name / /
27th Author's Affiliation ()
()
28th Author's Name / /
28th Author's Affiliation ()
()
29th Author's Name / /
29th Author's Affiliation ()
()
30th Author's Name / /
30th Author's Affiliation ()
()
31st Author's Name / /
31st Author's Affiliation ()
()
32nd Author's Name / /
32nd Author's Affiliation ()
()
33rd Author's Name / /
33rd Author's Affiliation ()
()
34th Author's Name / /
34th Author's Affiliation ()
()
35th Author's Name / /
35th Author's Affiliation ()
()
36th Author's Name / /
36th Author's Affiliation ()
()
Speaker Author-1 
Date Time 2026-02-17 09:40:00 
Presentation Time 20 minutes 
Registration for HI 
Paper # HI2026-1 
Volume (vol) vol.50 
Number (no) no.4 
Page pp.1-5 
#Pages
Date of Issue 2026-02-10 (HI) 


[Return to Top Page]

[Return to ITE Web Page]


The Institute of Image Information and Television Engineers (ITE), Japan