K
Kinh Tieu
Researcher at Massachusetts Institute of Technology
Publications - 31
Citations - 2238
Kinh Tieu is an academic researcher from Massachusetts Institute of Technology. The author has contributed to research in topics: Image retrieval & Feature vector. The author has an hindex of 16, co-authored 31 publications receiving 2206 citations. Previous affiliations of Kinh Tieu include Mitsubishi Electric Research Laboratories & Yale University.
Papers
More filters
Proceedings ArticleDOI
Boosting image retrieval
Kinh Tieu,Paul A. Viola +1 more
TL;DR: An approach for image retrieval using a very large number of highly selective features and efficient online learning based on the assumption that each image is generated by a sparse set of visual "causes" and that images which are visually similar share causes.
Journal ArticleDOI
Boosting Image Retrieval
Kinh Tieu,Paul A. Viola +1 more
TL;DR: This work proposes a mechanism for computing a very large number of highly selective features which capture some aspects of this causal structure and shows results on a wide variety of image queries.
Book ChapterDOI
Learning semantic scene models by trajectory analysis
TL;DR: An unsupervised learning framework to segment a scene into semantic regions and to build semantic scene models from long-term observations of moving objects in the scene is described and novel clustering algorithms which use both similarity and comparison confidence are introduced.
Proceedings ArticleDOI
Fully automatic pose-invariant face recognition via 3D pose normalization
TL;DR: This paper proposes a 3D pose normalization method that is completely automatic and leverages the accurate 2D facial feature points found by the system and outperforms other comparable methods convincingly.
Proceedings ArticleDOI
Inference of non-overlapping camera network topology by measuring statistical dependence
TL;DR: An approach for inferring the topology of a camera network by measuring statistical dependence between observations in different cameras is presented, accomplished by non-parametric estimates of statistical dependence and Bayesian integration of the unknown correspondence.