CRESS seminar: Dr. Sheng Tang (Chinese Academy of Sciences)
Time: Friday, January 24, 2pm
Location: M1.08, Reykjavík University, Menntavegur 1
Title: Sparse Ensemble Learning for Visual Concept Detection
Speaker: Dr. Sheng Tang, Institute of Computing Technology, Chinese Academy of Sciences (ICT-CAS), China
Abstract: Visual concept detection aims to automatically annotate visual data such as images and videos with respect to a semantic concept which can serve as good intermediate semantic features for video content indexing and understanding, and thus, spurring much research attention. In this talk, we present a novel sparse ensemble learning scheme for visual concept detection. In order to improve both training and testing efficiencies for large sale training dataset, the proposed ensemble first exploits a sparse non-negative matrix factorization (NMF) process to represent data instances in parts and partition the data space into localities, and then coordinates the individual classifiers in each locality for final classification. In the sparse NMF, data exemplars are projected to a set of locality bases, in which the non-negative superposition of basis images reconstructs the original exemplars. This additive combination ensures that each locality captures the characteristics of data exemplars in part, thus enabling the local classifiers to hold reasonable diversity in their own regions of expertise. More importantly, the sparse NMF ensures that an exemplar is projected to only a few bases (localities) with non-zero coefficients. The resulting ensemble model is, therefore, sparse, in the way that only a small number of efficient classifiers in the ensemble will fire on a testing sample.
Bio: Sheng Tang received his Ph.D. degree in computer application technology at the Institute of Computing Technology, Chinese Academy of Sciences (ICT-CAS), China, in March 2006. He is now an associate professor in the ICT-CAS. From 2006 to 2008, he was the TRECVid team (MCG-ICT-CAS) leader of the Multimedia Computing Group at ICT-CAS. From Feb., 2009 to Feb., 2010, he worked as a visiting research fellow in NUS under the instruction of Prof. Chua Tat-Seng. His current research interests are in the fields of pattern recognition and machine learning, multimedia information processing, in particular, on indexing, retrieval and extraction of information in image and video. Dr. Tang is a member of ACM, IEEE, and senior member of China Computer Federation (CCF). He serves as the reviewer for a number of famous international conferences and journals, such as ACM Transactions on Intelligent Systems and Technology, IEEE Transactions on Circuits and Systems for Video Technology, IEEE Transactions on Information Forensics & Security, Journal of Visual Communication and Image, etc.