by Sarah Frigg | Dec 11, 2015 | Capture, Visual Computing
Photogeometric Scene Flow for High-Detail Dynamic 3D Reconstruction This paper proposes photogeometric scene flow (PGSF) for high-quality dynamic 3D reconstruction. December 11, 2015International Conference on Computer Vision (ICCV) 2015 Authors Paulo F. U....
by Sarah Frigg | Nov 9, 2015 | Uncategorized
Toward Better Understanding of Engagement in Multiparty Spoken Interaction with Children We introduce a concrete metric for engagement—willingness to continue the interaction—that leads to better inter-coder judgments for children playing in pairs. November 9,...
by Martina Megaro | Jun 7, 2015 | Machine Learning
Space-Time Tree Ensemble for Action Recognition We explore ensembles of hierarchical spatio-temporal trees, discovered directly from training data, to model these structures for action recognition. June 7, 2015IEEE Conference on Computer Vision Pattern Recognition...
by Martina Megaro | Jun 23, 2014 | Machine Learning, Video Processing, Visual Computing
Jointly Summarizing Large-Scale Web Images and Videos for the Storyline Reconstruction In this paper, we address the problem of jointly summarizing large-scale Flickr images and YouTube user videos. June 23, 2014IEEE Conference on Computer Vision Pattern Recognition...
by Martina Megaro | Dec 9, 2013 | Visual Computing, Wireless Communication and Ubiquitous Computing
RFID Shakables: Pairing Radio-Frequency Identification Tags with the Help of Gesture Recognition A novel approach for pairing RFID-enabled devices is introduced and evaluated in this work. December 9, 2013ACM Conference on Emerging Networking Experiments and...
