Dr. Longbin Jin | Signal Processing Awards | Best Researcher Award
Dr. Longbin Jin, Konkuk University, South Korea
Professional Profile:
Research for Community Impact Award: Longbin Jin’s Suitability
Longbin Jin is a highly qualified candidate for the Research for Community Impact Award due to his significant contributions in the fields of artificial intelligence and healthcare, particularly in projects that directly benefit the community.
📚 Education
- Ph.D. in Computer Science
Konkuk University, Korea
Expected: February 2025
Thesis: Adaptive Visual Prompting for Video Action Recognition in Vision-Language Models
Advisor: Prof. Eun Yi Kim - M.S. in Smart ICT Convergence
Konkuk University, Korea
Graduated: August 2020
Thesis: E-EmoticonNet: EEG-based Emotion Recognition with Context Information
Advisor: Prof. Eun Yi Kim - B.S. in Mechanical Engineering & Automation
Shanghai University, China
Graduated: August 2018
💼 Work Experience
- AI Researcher
Voinosis, Seoul, Korea
December 2022 – Present- Researcher on AI models for early detection of hearing loss and cognitive impairment based on voice analysis for the elderly (VoiceCheck & BrainGuardDoctor Apps).
- Instructor
Konkuk University, Seoul, Korea
March 2022 – Present- Teaching courses on Computer Vision, Artificial Intelligence, and Machine Learning.
- AI Engineer
Lulla, Seoul, Korea
October 2022 – November 2022- Main researcher for an AI model for a child face-matching system to assist kindergarten teachers (Lulla App).
🏆 Achievements, Awards, and Honors
- Winner of ICASSP 2023 SPGC Challenge: Multilingual Alzheimer’s Dementia Recognition through Spontaneous Speech (First Author) 🥇
- Excellence Prize, Korea Software Congress 2023 🥇
- Encouragement Prize, ACM Student Research Competition, Computer Human Interaction 2020 (First Author) 🎖️
- Excellence Prize, Korea Software Congress 2019 (First Author) 🏅
- Encouragement Prize, Korea Software Congress 2019 (First Author) 🎖️
- Excellent Presentation, International Conference on Culture Technology 2018 🌟
Publication Top Notes:
Interpretable Cross-Subject EEG-Based Emotion Recognition Using Channel-Wise Features†
CITED:29
CITED:15
Eeg-based user identification using channel-wise features
CITED:7
E-EmotiConNet: EEG-based emotion recognition with context information
CITED:2
Emotion Recognition based BCI using Channel-wise Features
CITED:1