mugshot-tatjencham

CHAM, Tat Jen

BA PhD Cambridge

 

Associate Professor

School of Computer Science & Engineering

Nanyang Technological University

Singapore

 

Biographical Sketch

Tat-Jen is an Associate Professor in the School of Computer Science & Engineering, Nanyang Technological University. He received his BA in Engineering in 1993 and his PhD in 1996, both from the University of Cambridge. Tat-Jen was subsequently conferred a Jesus College Research Fellowship in Science in 1996-97. From 1998 to 2001, he was a research scientist at DEC/Compaq Research Lab in Cambridge, MA, USA. After joining NTU in 2002, he was concurrently a Faculty Fellow in the Singapore-MIT Alliance Computer Science Program in 2003-2006.

In research., Tat-Jen received overall best paper prizes at PROCAMS’05, BMVC’94, and in particular at ECCV'96, while his PhD student Minh-Tri Pham was awarded the PREMIA 2nd best student paper prize for their ICCV'2007 paper. Tat-Jen is an inventor on eight patents. He is currently a co-Principal Investigator in the NRF BeingTogether Centre (BTC) on 3D Telepresence, a collaboration between NTU and UNC at Chapel Hill.

Tat-Jen is on the editorial board for the International Journal of Computer Vision (IJCV). He has been a General Chair for ACCV’14, Area Chair for ICCV'09, ACCV’07, ICCV’05 and ACCV’06, Associate Editor for IJIG and IPSJ-CVA, a Program Chair for MMM’07, and a co-founder for the PROCAMS workshop series in 2003. Nationally, he has been on various review panels for A*STAR and the National Research Foundation (NRF). Tat-Jen has served for a number of terms on the NTU Senate, and previous roles held include being the Director for the Centre for Multimedia & Network Technology (CeMNet) and an affiliate faculty with the Singapore-ETH Centre’s Future Cities Lab.

Tat-Jen’s research interests are broadly in computer vision and machine learning. Currently, his BTC team has focused on high-fidelity 3D dynamic reconstruction of humans and room environments with casually placed sensors, via deep learning approaches for semantic understanding to enable accurate reconstruction in the presence of clutter, occlusion and limited sensor coverage. His previous work includes image-based localization in urban environments, object matching and registration, human tracking, activity recognition, as well as projector-camera systems to turn all surfaces into ubiquitous interactive displays.

Concurrent and Past Appointments

·         2001-, Associate Professor, School of Computer Science & Engineering, NTU

·         2018-, 2010-14, Senator, NTU Senate

·         2007-15, Director, Centre for Multimedia & Network Technology (CeMNet)

·         2003-06, Singapore-MIT Alliance Fellow in Computer Science

·         2005-16, Part-time national service, infantry / civil-military relations officer, Singapore Armed Forces

·         1998-2001, Research Scientist, DEC / Compaq Cambridge Research Laboratory, Cambridge MA, USA

·         1996-97, Jesus College Research Fellow in Science, University of Cambridge, England

·         1987-90, Full-time national service: infantry / logistics officer, Singapore Armed Forces

Education

·         1994-96, Ph.D degree, St Catharine's College, University of Cambridge, England

·         1990-93, B.A. degree in Engineering, triple first-class honours, St Catharine's College, University of Cambridge, England

Awards and Scholarships

·         2014, MMSP Top 10% Paper Award

·         2007 (with PhD student Minh-Tri Pham), PREMIA 2nd Best Student Paper Prize for ICCV'07 paper

·         2005, Best Paper Award, IEEE International Workshop on Projector-Camera Systems (PROCAMS)

·         1996, Best Paper Prize, European Conference on Computer Vision (ECCV)

·         1994, Best Science Paper Prize, British Machine Vision Conference (BMVC)

·         1994-96, UK Overseas Research Scholarship, Cambridge Commonwealth Trust Bursary, St Catharine's College Research Scholarship (all awarded concurrently)

·         1993, Alexandria Prize, St Catharine's College Senior Scholarship

·         1991, Engineering Members' Prize

·         1990-94, Loke Cheng-Kim Foundation Scholarship

Selected Professional Activities

·         2004-, Member of Editorial Board, International Journal of Computer Vision (IJCV), Kluwer publishers

·         General Chair, Asian Conference on Computer Vision (ACCV), Singapore, 2014

·         Area Chair, International Conference on Computer Vision (ICCV), Kyoto, Japan, 2009

·         Area Chair, Asian Conference on Computer Vision (ACCV), Tokyo, Japan, 2007

·         Area Chair, Asian Conference on Computer Vision (ACCV), Hyderabad, India, 2006

·         Area Chair, International Conference on Computer Vision (ICCV), Beijing, China, 2005

·         Associate Editor, International Journal of Image and Graphics (IJIG), World Scientific, 2005

·         Associate Editor, IPSJ Transactions on Computer Vision and Applications (CVA), 2008

Recent and Selected Papers

·         Chuanxia Zheng, Tat-Jen Cham, Jianfei Cai, T2Net: Synthetic-to-realistic translation for solving single-image depth estimation tasks. ECCV, 2018

·         Di Xu, Qi Duan, Jianmin Zheng, Juyong Zhang, Jianfei Cai, Tat-Jen Cham, Shading-based surface detail recovery under general unknown illumination. IEEE TPAMI, 40(2): 423-436, 2018

·         Anran Wang, Jianfei Cai, Jiwen Lu, Tat-Jen Cham, Structure-aware multimodal feature fusion for RGB-D scene classification and beyond. ACM TOMM, 14(2s): 39:1-39:22, 2018

·         Xinxing Xia, Yunqing Guan, Andrei State, Tat-Jen Cham, Henry Fuchs, Towards efficient 3D calibration for different types of multi-view autostereoscopic 3D displays. CGI, 2018

·         Teng Deng, Jianfei Cai, Tat-Jen Cham, Jianmin Zheng, Multiple consumer-grade depth camera registration using everyday objects. Image & Vision Computing, 62: 1-7, 2017

·         Lu Sheng, Jianfei Cai, Tat-Jen Cham, Vladimir Pavlovic, King Ngi Ngan, A generative model for depth-based robust 3D facial pose tracking. CVPR, 2017

·         Fuwen Tan, Chi-Wing Fu, Teng Deng, Jianfei Cai, Tat-Jen Cham, FaceCollage: a rapidly deployable system for real-time head reconstruction for on-the-go 3D telepresence. ACM Multimedia, 2017

·         Anran Wang, Jianfei Cai, Jiwen Lu, Tat-Jen Cham, Modality and component aware feature fusion for RGB-D scene classification, CVPR, 2016

·         Anran Wang, Jiwen Lu, Jianfei Cai, Gang Wang, Tat-Jen Cham, Unsupervised joint feature learning and encoding for RGB-D scene labeling, IEEE TIP, 24(11): 4459-4473, 2015

·         Chongyu Chen, Jianfei Cai, Jianmin Zheng, Tat-Jen Cham, Guangming Shi, Kinect depth recovery using a color-guided, region-adaptive, and depth-selective framework. ACM TIST, 6(2): 12:1-12:19, 2015

·         Marcus Chen, Ivor W. Tsang, Mingkui Tan, Tat-Jen Cham, A unified feature selection framework for graph embedding on high dimensional data. IEEE TKDE, 27(6): 1465-1477, 2015

·         Anran Wang, Jiwen Lu, Jianfei Cai, Tat-Jen Cham, Gang Wang, Large-margin multi-modal deep learning for RGB-D object recognition. IEEE TMM, 17(11): 1887-1898, 2015

·         Anran Wang, Jianfei Cai, Jiwen Lu, Tat-Jen Cham, MMSS: Multi-modal sharable and specific feature learning for RGB-D object recognition. ICCV, 2015

·         Di Xu, Qi Duan, Jianming Zheng, Juyong Zhang, Jianfei Cai, Tat-Jen Cham. Recovering surface details under general unknown illumination using shading and coarse multi-view stereo. CVPR, 2014

·         Anran Wang, Jiwen Lu, Gang Wang, Jianfei Cai, Tat-Jen Cham, Multi-modal unsupervised feature learning for RGB-D scene labeling. ECCV, 2014

·         Anran Wang, Jiwen Lu, Jianfei Cai, Gang Wang, Tat-Jen Cham, Estimating spatial layout of rooms from RGB-D videos. MMSP, 2014. Top 10% paper.

·         Cédric Fleury, Tiberiu Popa, Tat-Jen Cham, Henry Fuchs, Merging live and pre-captured data to support full 3D head reconstruction for telepresence. Eurographics (Short Papers), 2014

·         Yi Huang, Dong Xu, Tat-Jen Cham, Face and human gait recognition using image-to-class distance. IEEE T-CSVT, 2010

·         Dong Xu, Tat-Jen Cham, Shuicheng Yan, Lixin Duan, Shih-Fu Chang, Near duplicate identification with spatially aligned pyramid matching. IEEE T-CSVT, 2010

·         Tat-Jen Cham, Arridhana Ciptadi, Wei-Chian Tan, Minh-Tri Pham, Liang-Tien Chia, Estimating camera pose from a single urban ground-view omnidirectional image and a 2D building outline map. CVPR, 2010. CVPR oral paper.

·         Minh-Tri Pham, Yang Gao, Viet-Dung Hoang, Tat-Jen Cham, Fast polygonal integration and its application in extending Haar-like features to improve object detection. CVPR, 2010

·         Minh-Tri Pham, V-D. D. Hoang, Tat-Jen Cham, Detection with multi-exit asymmetric boosting. CVPR, 2008

·         Dong Xu, Tat-Jen Cham, Shuicheng Yan, Shih-Fu Chang, Near duplicate image identification with patially aligned pyramid matching, CVPR, 2008

·         Minh-Tri Pham, Tat-Jen Cham, Fast training and selection of Haar features using statistics in boosting-based face detection. ICCV, 2007. ICCV oral paper. PREMIER 2nd best student paper prize (among all Singapore research papers in field of pattern recognition).

·         Minh-Tri Pham, Tat-Jen Cham, Online learning asymmetric boosted classifiers for object detection. CVPR, 2007. CVPR oral paper.

·         Michael S. Brown, Peng Song, Tat-Jen Cham, Image pre-conditioning for out-of-focus projector blur. CVPR, 2006.

·         Peng Song, Tat-Jen Cham, A theory for photometric self-calibration of multiple overlapping projectors and cameras. PROCAMS, 2005. Best paper prize.

·         Xi Chen, Tat-Jen Cham, Learning feature distance measures for image correspondences. CVPR, 2005.

·         Tat-Jen Cham, James M. Rehg, Rahul Sukthankar, Gita Sukthankar, Shadow elimination and occluder light suppression for multi-projector displays. CVPR, 2003.

·         David E. DiFranco, Tat-Jen Cham, James M. Rehg, Reconstruction of 3-D figure motion from 2-D correspondences. CVPR, 2001. CVPR oral paper.

·         Rahul Sukthankar, Tat-Jen Cham, Gita Sukthankar, Dynamic shadow elimination for multi-projector displays. CVPR, 2001.

·         Tat-Jen Cham, Roberto Cipolla, Automated b-spline curve representation incorporating MDL and error-minimizing control point insertion strategies, IEEE TPAMI, 21(1): 49-53, 1999

·         Tat-Jen Cham, James M. Rehg, A multiple hypothesis approach to figure tracking. CVPR, 1999. CVPR oral paper.

·         Tat-Jen Cham, James M. Rehg, Dynamic feature ordering for efficient registration. ICCV, 1999. ICCV oral paper.

·         Vladimir Pavlovic, James M. Rehg, Tat-Jen Cham, Kevin P. Murphy, A dynamic Bayesian network approach to figure tracking using learned dynamic models. ICCV, 1999. ICCV oral paper.

·         Tat-Jen Cham, Roberto Cipolla, A statistical framework for long-range feature matching in uncalibrated image mosaicing. CVPR, 1998.

·         Tat-Jen Cham, Roberto Cipolla, Stereo coupled active contours. CVPR, 1997. CVPR oral paper.

·         Tat-Jen Cham, Roberto Cipolla, Geometric saliency of curve correspondances and grouping of symmetric contours, ECCV, 1996. ECCV best paper prize.

·         Tat-Jen Cham, Roberto Cipolla, Skewed symmetry detection through local skewed symmetries. BMVC, 1994. BMVC best science paper prize.

Miscellaneous

·         2010, World's fastest software-based face detector, released by Minh-Tri Pham. Ran 3-4 times faster than the OpenCV implementation. Available here.

·         Jointly-taught SMA graduate module resulted in game-related student projects that received substantial media coverage from Channel News Asia, Lianhe Zaobao and Tamil Murasu, 2004.