H
Hong-Wei Ng
Researcher at University of Illinois at Urbana–Champaign
Publications - 5
Citations - 1303
Hong-Wei Ng is an academic researcher from University of Illinois at Urbana–Champaign. The author has contributed to research in topics: Audio signal processing & Deep learning. The author has an hindex of 4, co-authored 5 publications receiving 1030 citations.
Papers
More filters
Proceedings ArticleDOI
A data-driven approach to cleaning large face datasets
Hong-Wei Ng,Stefan Winkler +1 more
TL;DR: An approach to building face datasets that starts with detecting faces in images returned from searches for public figures on the Internet, followed by discarding those not belonging to each queried person, and is releasing the FaceScrub dataset.
Proceedings ArticleDOI
Deep Learning for Emotion Recognition on Small Datasets using Transfer Learning
TL;DR: This paper presents the techniques employed in the team's submissions to the 2015 Emotion Recognition in the Wild contest, for the sub-challenge of Static Facial Expression Recognition In the Wild.
Proceedings ArticleDOI
The 9th annual MLSP competition: New methods for acoustic classification of multiple simultaneous bird species in a noisy environment
Forrest Briggs,Yonghong Huang,Raviv Raich,Konstantinos Eftaxias,Zhong Lei,William Cukierski,Sarah Frey Hadley,Adam S. Hadley,Matthew G. Betts,Xiaoli Z. Fern,Jed Irvine,Lawrence Neal,Anil Thomas,Gabor Fodor,Grigorios Tsoumakas,Hong-Wei Ng,Thi Ngoc Tho Nguyen,Heikki Huttunen,Pekka Ruusuvuori,Tapio Manninen,Aleksandr Diment,Tuomas Virtanen,Julien Marzat,Joseph Defretin,David R. Callender,Chris Hurlburt,Ken Larrey,Maxim Milakov +27 more
TL;DR: It is an open problem for signal processing and machine learning to reliably identify bird sounds in real-world audio data collected in an acoustic monitoring scenario.
Proceedings ArticleDOI
Brush-and-drag: a multi-touch interface for photo triaging
TL;DR: An effective and easy-to-use brush-and-drag interface that allows the user to interactively explore and compare photos within a broader scene context and demonstrates to offer effective interactions in a user study.
Proceedings ArticleDOI
The 9th annual MLSP competition: Second place
Hong-Wei Ng,Thi Ngoc Tho Nguyen +1 more
TL;DR: The MLSP 2013 Bird Classification Challenge requires participants to predict the set of bird species present in audio clips in a given test set, with the aim of maximizing the micro-AUC score computed from the predictions.