Structure-Focused Multi-task Learning Approach for structural pattern recognition and analysis

Research Project

Project/Area Number	24K20789
Research Category	Grant-in-Aid for Early-Career Scientists
Allocation Type	Multi-year Fund
Review Section	Basic Section 61010:Perceptual information processing-related
Research Institution	Tokyo University of Agriculture and Technology
Principal Investigator	LY TUAN・NAM 東京農工大学, 工学(系)研究科(研究院), 特任助教 (10975171)
Project Period (FY)	2024-04-01 – 2027-03-31
Project Status	Granted (Fiscal Year 2024)
Budget Amount *help	¥4,680,000 (Direct Cost: ¥3,600,000、Indirect Cost: ¥1,080,000) Fiscal Year 2026: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000) Fiscal Year 2025: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000) Fiscal Year 2024: ¥2,600,000 (Direct Cost: ¥2,000,000、Indirect Cost: ¥600,000)
Keywords	multi-task learning / structural patterns / pattern recognition / document analysis
Outline of Research at the Start	This research formulates the problem of structural pattern recognition as a multi-task learning problem and proposes a structure-focused multi-task learning network that can be applied or easily extended to all data types of structural patterns.