UVR Lab. was formed in Feb. 2001 at GIST to study and develop “Virtual Reality in Smart computing environments” that process multimodal input, perceive user’s intention and emotion, and respond to user’s request through Augmented Reality. Since 2012, UVR Lab moved to KAIST GSCT and restarted with a theme of “FUN in Ubiquitous VR.”
작성일 : 15-08-14
[UVR Seminar] by Prof.Tae-Kyun Kim at ICL (8/21/2015)
 글쓴이 : UVR
조회 : 5,322  

- Title:  Tree-Structured Classifiers for Pose Estimation

- Date & Time: 21(Fri.)/Aug/2015, 13:00~15:00

- Venue: N25 #3239 (Laughlin Hall)

- Speaker: Prof.Tae-Kyun Kim (Assistant Professor, Computer Vision and Learning Lab., Imperial College London)


Abstract: Many computer vision tasks can be cast as large-scale classification problems, where extremely efficient and powerful classification methods are pursued. Boosting with decision stump learners, the state-of-the-art for objet detection, can be seen as a flatstructure, while many developments including a Boosting cascade can be seen as a deeper tree structure. Randomised Decision Forests is an emerging technique in the fields. A hierarchical structure yields many short paths, accelerating evaluation time, while feature randomisation promotes good generalisation to unseen data. It is inherently for multi-class classification problems. In this talk, we see applications of Randomised Decision Forests and tree-structured methods with comparisons and insights. The talk focuses on articulated hand pose estimation, and face recognition/landmarking. Hand and face are highly articulated and deformable objects, playing a key role for novel man-machine interfaces. Estimating their 3D postures, or regressing locations of joints/fiducial points is highly challenging. We have tackled the problems by various novel ideas on top of the cutting-edge techniques. We conclude the talk with some future directions including 6DOF object pose estimation and active interactive object recognition.


More information is found at


BioTae-Kyun Kim is an Assistant Professor and leader of Computer Vision and Learning Lab at Imperial College London, UK, since Nov 2010. He obtained his PhD from Univ. of Cambridge in 2008 and Junior Research Fellowship (governing body) of Sidney Sussex College, Univ. of Cambridge for 2007-2010. His research interests primarily lie in decision forests (tree-structure classifiers) and linear methods for: articulated hand pose estimation, face analysis and recognition by image sets and videos, 6D object pose estimation, active robot vision, activity recognition, object detection/tracking, etc. which lead to novel active and interactive vision. He has co-authored over 40 academic papers in top-tier conferences and journals in the field, his co-authored algorithm for face image retrieval is an international standard of MPEG-7 ISO/IEC. He is co-recipient of the KUKA best service robotics paper award at ICRA 2014, and organising co-chair of CVPR15 workshop on HANDS and ICCV15 workshop on Object Pose.