Publications
101 results found
Luo W, Kim T-K, Stenger B, et al., 2014, Bi-label Propagation for Generic Multiple Object Tracking, 27th IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Publisher: IEEE, Pages: 1290-1297, ISSN: 1063-6919
- Author Web Link
- Cite
- Citations: 20
Tang D, Chang HJ, Tejani A, et al., 2014, Latent Regression Forest: Structured Estimation of 3D Articulated Hand Posture, 27th IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Publisher: IEEE, Pages: 3786-3793, ISSN: 1063-6919
- Author Web Link
- Cite
- Citations: 206
Pei Y, Kim T-K, Zha H, 2013, Unsupervised Random Forest Manifold Alignment for Lipreading, IEEE Int. Conf. on Computer Vision (ICCV)
Tang D, Yu T, Kim T-K, 2013, Real-time Articulated Hand Pose Estimation using Semi-supervised Transductive Regression Forests, IEEE Int. Conf. on Computer Vision (ICCV)
Lee K, Su Y, Kim T-K, et al., 2013, A syntactic approach to robot imitation learning using probabilistic activity grammars, Robotics and Autonomous Systems, Vol: 61, Pages: 1323-1334, ISSN: 0921-8890
This paper describes a syntactic approach to imitation learning that captures important task structures in the form of probabilistic activity grammars from a reasonably small number of samples under noisy conditions. We show that these learned grammars can be recursively applied to help recognize unforeseen, more complicated tasks that share underlying structures. The grammars enforce an observation to be consistent with the previously observed behaviors which can correct unexpected, out-of-context actions due to errors of the observer and/or demonstrator. To achieve this goal, our method (1) actively searches for frequently occurring action symbols that are subsets of input samples to uncover the hierarchical structure of the demonstration, and (2) considers the uncertainties of input symbols due to imperfect low-level detectors.We evaluate the proposed method using both synthetic data and two sets of real-world humanoid robot experiments. In our Towers of Hanoi experiment, the robot learns the important constraints of the puzzle after observing demonstrators solving it. In our Dance Imitation experiment, the robot learns 3 types of dances from human demonstrations. The results suggest that under reasonable amount of noise, our method is capable of capturing the reusable task structures and generalizing them to cope with recursions.
Luo W, Kim T-K, 2013, Generic Object Crowd Tracking by Multi-Task Learning, British Machine Vision Conference (BMVC)
Yu T, Kim T-K, Cipolla R, 2013, Unconstrained Monocular 3D Human Pose Estimation by Action Detection and Cross-modality Regression Forest, IEEE Conf. on Computer Vision and Pattern Recognition (CVPR)
Lee K, Kim TK, Demiris Y, 2012, Learning Action Symbols for Hierarchical Grammar Induction, Tsukuba, Japan, International Conference on Pattern Recognition (ICPR), Publisher: IEEE, Pages: 3778-3782
We present an unsupervised method of learning action symbols from video data, which self-tunes the number of symbols to effectively build hierarchical activity grammars. A video stream is given as a sequence of unlabeled segments. Similar segments are incrementally grouped to form a hierarchical tree structure. The tree is cut into clusters where each cluster is used to train an action symbol. Our goal is to find a good set of clusters i.e. symbols where regularities are best captured in the learned representation, i.e. induced grammar. Our method has two-folds: 1) Create a candidate set of symbols from initial clusters, 2) Build an activity grammar and measure model complexity and likelihood to assess the quality of the candidate set of symbols. We propose a balanced model comparison method which avoids the problem commonly found in model complexity computations where one measurement term dominates the other. Our experiments on the towers of Hanoi and human dancing videos show that our method can discover the optimal number of action symbols effectively.
Lee K, Kim T-K, Demiris Y, 2012, Learning Action Symbols for Hierarchical Grammar Induction, International Conference on Pattern Recognition (ICPR)
Xiong C, Kim T-K, 2012, Set-Based Label Propagation of Face Images, IEEE International Conference on Image Processing
Tang D, Liu Y, Kim T-K, 2012, Fast Pedestrian Detection by Cascaded Random Forest with Dominant Orientation Templates, British Machine Vision Conference (BMVC)
Lee K, Kim TK, Demiris Y, 2012, Learning Reusable Task Components using Hierarchical Activity Grammars with Uncertainties, St. Paul, Minnesota, USA, Publisher: IEEE, Pages: 1994-1999
We present a novel learning method using activity grammars capable of learning reusable task components from a reasonably small number of samples under noisy conditions. Our linguistic approach aims to extract the hierarchical structure of activities which can be recursively applied to help recognize unforeseen, more complicated tasks that share the same underlying structures. To achieve this goal, our method 1) actively searches for frequently occurring action symbols that are subset of input samples to effectively discover the hierarchy, and 2) explicitly takes into account the uncertainty values associated with input symbols due to the noise inherent in low-level detectors. In addition to experimenting with a synthetic dataset to systematically analyze the algorithm's performance, we apply our method in human-led imitation learning environment where a robot learns reusable components of the task from short demonstrations to correctly imitate more complicated, longer demonstrations of the same task category. The results suggest that under reasonable amount of noise, our method is capable to capture the reusable structures of tasks and generalize to cope with recursions.
Kim T-K, Cipolla R, 2012, Multiple Classifier Boosting and Tree-Structured Classifiers, Machine Learning for Computer Vision, Editors: Cipolla, Battiato, Farinella, Publisher: Springer, ISBN: 9783642286605
Kim T-K, Budvytis I, Cipolla R, 2012, Making a Shallow Network Deep: Conversion of a Boosting Classifier into a Decision Tree by Boolean Optimisation, International Journal of Computer Vision, Vol: 100, Pages: 203-215
Cho I, Kim T, 2011, Apparatus and method for providing security in a base or mobile station by using detection of face information, US7864988
Chen Y, Kim T-K, Cipolla R, 2011, Silhouette-based Object Phenotype Recognition using 3D Shape Priors, Int. Conference on Computer Vision
Kim T-K, Stenger B, Kittler J, et al., 2011, Incremental Linear Discriminant Analysis Using Sufficient Spanning Sets and Its Applications, International Journal of Computer Vision, Vol: 91, Pages: 216-233
Hwang W, Kim T, 2010, Face recognition apparatus and method using PCA learning per subgroup, US7734087
Kim T-K, Stenger B, Woodley T, et al., 2010, Multiple Classifier Boosting for Object Tracking, IEEE CVPR workshop on Online Learning for Computer Vision
Kim T-K, Kittler J, Cipolla R, 2010, On-line Learning of Mutually Orthogonal Subspaces for Face Recognition by Image Sets, IEEE Trans. on Image Processing, Vol: 19, Pages: 1067-1074
Yu TH, Kim T-K, Cipolla R, 2010, Real-time Action Recognition by Spatiotemporal Semantic and Structural Forest, British Machine Vision Conference
Bonde U, Kim T-K, Ramakrishnan K, 2010, Randomised Manifold Forests for Principal Angle based Face Recognition, Asian Conf. on Computer Vision
Chen Y, Kim T-K, Cipolla R, 2010, Inferring 3D Shapes and Deformations from Single Views, European Conference on Computer Vision
Kim T-K, Budvytis I, Cipolla R, 2010, Making a Shallow Network Deep: Growing a Tree from Decision Regions of a Boosting Classifier, British Machine Vision Conference
Chaiyasarn K, Kim T-K, Cipolla R, et al., 2009, Image Mosaicing via Quadric Surface Estimation with Priors for Tunnel Inspection, IEEE Int. Conf. on Image Processing, Pages: 537-540
Mavaddat N, Kim T-K, Cipolla R, 2009, Design and evaluation of features that best define text in complex scene images, IAPR Conf. on Machine Vision Applications, Pages: 94-97
Stenger B, Woodley T, Kim T-K, et al., 2009, A Vision-based Interface for Display Interaction, The 23rd BCS Conf. on Human Computer Interaction, Pages: 163-168
Kim T-K, Cipolla R, 2009, Canonical Correlation Analysis of Video Volume Tensors for Action Categorization and Detection, IEEE Trans. on Pattern Analysis and Machine Intelligence, Vol: 31, Pages: 1415-1428
This data is extracted from the Web of Science and reproduced under a licence from Thomson Reuters. You may not copy or re-distribute this data in whole or in part without the written consent of the Science business of Thomson Reuters.