Hancheol Park
I am a researcher dedicated to creating practical AI systems that are reliable and computationally efficient, while also delivering high performance 👍
Education
Ph.D., School of Computing, KAIST
Research Interest
Domains: natural language processing and computer vision
Topics: uncertainty and model compression
Awards
ACL 2023 Outstanding Paper Award
KCC 2023 Best Presentation Award
NVIDIA Applied Research Accelerator Award, 2022-2023
HCLT 2016 Best Paper Award
KCC 2016 Best Paper Award
AFNLP Best Asian Paper Award
Challenges
2023 AI City Challenge Track 1: Multi-Camera People Tracking (Top 10)
Visual Object Tracking 2023 Challenge (2nd place out of 47 teams in accuracy)
Publications
Hancheol Park and Jong C. Park. Deep Model Compression Also Helps Models Capture Ambiguity. ACL 2023 (Volume 1: Long Papers)
Fitsum Gaim, Wonsuk Yang, Hancheol Park, and Jong C. Park. Question-Answering in a Low-resourced Language: Benchmark dataset and Models for Tigrinya. ACL 2023 (Volume 1: Long Papers)
Kristan, ... , Hancheol Park, ... The First Visual Object Tracking Segmentation VOTS2023 Challenge Results. ICCV 2023 (Workshop: VOTS2023)
Bo-Kyeong Kim, Jaemin Kang, Daeun Seo, Hancheol Park, Shinkook Choi, Hyoung-Kyu Song, Hyungshin Kim, and Sungsu Lim. Accelerating Speech-Driven Talking Face Generation with 28x Compressed Wav2Lip, ICCV 2023 (Demo)
Bo-Kyeong Kim, Jaemin Kang, Daeun Seo, Hancheol Park, Shinkook Choi, Hyoung-Kyu Song, Hyungshin Kim, and Sungsu Lim. A Unified Compression Framework for Efficient Speech-Driven Talking-Face Generation, MLSys 2023 (Workshop: On-Device Intelligence Workshop)
최동혁, 신욱수, 박한철, 민기, 유영준. 가중 합 기반 특징 결합 디코더를 이용한 시멘틱 세그멘테이션 모델 경량화. KCC 2023
Jeongho Kim*, Wooksu Shin*, Hancheol Park*, and Jongwon Baek. Addressing the Occlusion Problem in Multi-Camera People Tracking With Human Pose Estimation. CVPR 2023 (Workshop: AI City Challenge) (* these authors contributed equally to this work)
Bo-Kyeong Kim, Shinkook Choi, and Hancheol Park. Cut Inner Layers: A Structured Pruning Strategy for Efficient U-Net GANs. ICML 2022 (Workshop: Hardware Aware Efficient Training)
Hancheol Park, Kyo-Joong Oh, Ho-Jin Choi, and Gahgene Gweon. Constructing Paraphrase Database for Agglutinative Languages. Data & Knowledge Engineering (DKE) 123, 2019 (SCIE, IF= 1.583)
이희제, 박한철, 양원석, 박종철. 분산 표상 기법을 이용한 단어의 비표준 의미 사용 탐지. HCIK 2018
송호윤, 박한철, 양원석, 박종철. 언어학적 패턴을 이용한 소셜 미디어 사용자의 우울증 증세 예측. KSC 2017
Hancheol Park, Jung-Ho Kim, and Jong C. Park. Addressing Low-Resource Problems in Statistical Machine Translation of Manual Signals in Sign Language. Journal of KIISE 44(2), 2017.
Jung-Ho Kim, Najoung Kim, Hancheol Park, and Jong C. Park. Enhanced Sign Language Transcription System via Hand Tracking and Pose Estimation. Journal of Computing Science and Engineering (JCSE) 10(3), 2016
박한철, 김정호, 박종철. 말뭉치 자원 희소성에 따른 통계적 수화 번역 문제의 해결. KCC 2016
Jong Myoung Kim, Hancheol Park, Gahgene Gweon, and Jeong Hur. The Correlation between Search Quality and Query Poplularity. IEEE BigComp 2016
Hancheol Park, Gahgene Gweon, and Jeong Heo. Affix Modification-based Bilingual Pivoting Method for Paraphrase Extraction in Agglutinative Languages. IEEE BigComp 2016
Jong Myoung Kim, Hancheol Park, Young-Seob Jeong, Ho-Jin Choi, Gahgene Gweon, and Jeong Hur. Measuring Popularity of Machine-generated Sentences using Term Count, Document Frequency, and Dependency Language Model. PACLIC 29 (2015)
Hancheol Park and Gahgene Gweon. Initiating Moderation in Problematic Smartphone Usage Patterns. CHI 2015 (Extended Abstract)
Hancheol Park, Gahgene Gweon, Ho-Jin Choi, Jeong Heo, and Pum-Mo Ryu. Sentential Paraphrase Generation for Agglutinative Languages Using SVM with a String Kernel. PACLIC 28 (2014)