H
Hongwen Kang
Researcher at Carnegie Mellon University
Publications - 9
Citations - 440
Hongwen Kang is an academic researcher from Carnegie Mellon University. The author has contributed to research in topics: Object (computer science) & Video compression picture types. The author has an hindex of 9, co-authored 9 publications receiving 428 citations. Previous affiliations of Hongwen Kang include University of Science and Technology of China.
Papers
More filters
Proceedings ArticleDOI
Space-Time Video Montage
TL;DR: A novel spacetime video summarization method which is called space-time video montage, which simultaneously analyzes both the spatial and temporal distribution in a video sequence, and extracts the visually informative space- time portions of the input videos.
Proceedings ArticleDOI
Discovering object instances from scenes of Daily Living
TL;DR: An approach to identify and segment objects from scenes that a person (or robot) encounters in Activities of Daily Living (ADL) by able to link pieces of visual information from multiple images and extract the consistent patterns.
Proceedings ArticleDOI
Image matching in large scale indoor environment
TL;DR: This paper proposes a novel image matching algorithm, named Re-Search, that is designed to cope with self-repetitive structures and confusing patterns in the indoor environment, and it matches a query image with a two-pass strategy.
Proceedings ArticleDOI
Large-scale bot detection for search engines
TL;DR: This work uses the CAPTCHA technique and simple heuristics to extract from the data logs a large set of training samples with initial labels, and develops a semi-supervised learning algorithm to take advantage of the unlabeled data to improve the classification performance.
Proceedings ArticleDOI
To learn representativeness of video frames
Hongwen Kang,Xian-Sheng Hua +1 more
TL;DR: This paper developed a method to examine and evaluate the representativeness of video frames based on learning users' perceptive evaluations, and observed that users have similar tendency in selecting the most representative frame for a certain video segment.