M
Matthew Turk
Researcher at Toyota Technological Institute at Chicago
Publications - 209
Citations - 33736
Matthew Turk is an academic researcher from Toyota Technological Institute at Chicago. The author has contributed to research in topics: Augmented reality & Facial recognition system. The author has an hindex of 55, co-authored 198 publications receiving 30972 citations. Previous affiliations of Matthew Turk include Massachusetts Institute of Technology & University of California.
Papers
More filters
Posted Content
Face Verification in Polar Frequency Domain: a Biologically Motivated Approach
TL;DR: In this article, a local-based face verification system based on a Pseudo-Fisher discriminator is proposed, where three eye regions are converted from the spatial to polar frequency domain by a Fourier-Bessel Transform.
Facial expression analysis on manifolds
Matthew Turk,Ya Chang +1 more
TL;DR: A probabilistic model based on manifold of facial expression can represent facial expression analytically and globally and the Regional FACS system provides a novel FACS recognition solution with objective measurement.
Book
Vision-Based Interaction
Matthew Turk,Gang Hua +1 more
TL;DR: The landscape of history, opportunities, and challenges in this area of vision-based interaction are discussed; the state-of-the-art and seminal works in detecting and recognizing the human body and its components are reviewed; both static and dynamic approaches to ""looking at people"" vision problems are explored; and the computer vision work is placed in the context of other modalities and multimodal applications.
Posted Content
Sparse Fusion for Multimodal Transformers.
TL;DR: Sparse Fusion Transformers (SFT) as discussed by the authors is a multimodal fusion method for transformers that performs comparably to existing state-of-the-art methods while having greatly reduced memory footprint and computation cost.
Proceedings ArticleDOI
High-order regularization for stereo color editing
TL;DR: This paper pioneers a method for local color editing on stereo image pairs by introducing recent advances in the field of image segmentation, thus allowing a user's edits in one view to be simultaneously performed in the other view.