Fred Tung

Bio

I am a postdoctoral fellow working with Greg Mori at Simon Fraser University. My research interests are in computer vision and machine learning, with a focus on developing efficient algorithms for searching large-scale visual data, and for training fast and lightweight deep neural networks for resource-constrained platforms. I received the Ph.D. degree in computer science from the University of British Columbia under the supervision of Jim Little.

ftung [at] sfu.ca

Teaching

Jan. 2016CPSC 425 Computer Vision (University of British Columbia)

Publications

Constraint-aware deep neural network compression
C. Chen, F. Tung, N. Vedula, and G. Mori
European Conference on Computer Vision (ECCV), 2018
[pdf | code]
CLIP-Q: Deep network compression learning by in-parallel pruning-quantization
F. Tung and G. Mori
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018
[pdf | code]
Multi-level residual networks from dynamical systems view
B. Chang, L. Meng, E. Haber, F. Tung, and D. Begert
International Conference on Learning Representations (ICLR), 2018
[pdf]
Exploiting points and lines in regression forests for RGB-D camera relocalization
L. Meng, F. Tung, J.J. Little, J. Valentin, and C.W. De Silva
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2018
[pdf]
Deep learning of player trajectory representations for team activity analysis
N. Mehrasa, Y. Zhong, F. Tung, L. Bornn, and G. Mori
Sloan Sports Analytics Conference, 2018
[pdf]
Fine-pruning: Joint fine-tuning and compression of a convolutional network with Bayesian optimization
F. Tung, S. Muralidharan, and G. Mori
British Machine Vision Conference (BMVC), 2017
[pdf | code]
The Raincouver scene parsing benchmark for self-driving in adverse weather and at night
F. Tung, J. Chen, L. Meng, and J.J. Little
IEEE Robotics and Automation Letters, vol. 2, no. 4, pp. 2188-2193, 2017
[pdf | project page]
Backtracking regression forests for accurate camera relocalization
L. Meng, J. Chen, F. Tung, J.J. Little, J. Valentin, and C.W. De Silva
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2017
[pdf, code]
MF3D: Model-free 3D semantic scene parsing
F. Tung and J.J. Little
IEEE International Conference on Robotics and Automation (ICRA), 2017
[pdf]
SSP: Supervised sparse projections for large-scale retrieval in high dimensions
F. Tung and J.J. Little
Asian Conference on Computer Vision (ACCV), 2016
[pdf | link | code]
Factorized binary codes for large-scale nearest neighbor search
F. Tung and J.J. Little
British Machine Vision Conference (BMVC), 2016
[pdf]
Exploiting random RGB and sparse features for camera pose estimation
L. Meng, J. Chen, F. Tung, J.J. Little, and C. De Silva
British Machine Vision Conference (BMVC), 2016
[pdf, data, code]
Scene parsing by nonparametric label transfer of content-adaptive windows
F. Tung and J.J. Little
Computer Vision and Image Understanding (CVIU), vol. 143, pp. 191-200, 2016
[pdf | link]
Improving scene attribute recognition using web-scale object detectors
F. Tung and J.J. Little
Computer Vision and Image Understanding (CVIU), vol. 138, pp. 86-91, 2015
[pdf | link]
Bank of quantization models: A data-specific approach to learning binary codes for large-scale retrieval applications
F. Tung, J. Martinez, H.H. Hoos, and J.J. Little
IEEE Winter Conference on Applications of Computer Vision (WACV), 2015
[pdf | link]
CollageParsing: Nonparametric scene parsing by adaptive overlapping windows
F. Tung and J.J. Little
European Conference on Computer Vision (ECCV), 2014
[pdf | link]
Improving scene attribute recognition using web-scale object detectors
F. Tung and J.J. Little
International Workshop on Parts and Attributes (at ECCV), 2014
Polynomial self-similarity for object classification
F. Tung and A. Wong
IEEE International Conference on Multimedia and Expo, short papers track, 2013
A decoupled approach to illumination-robust optical flow estimation
A. Kumar, F. Tung, A. Wong, and D.A. Clausi
IEEE Transactions on Image Processing, vol. 22, no. 10, pp. 4136-4147, 2013
Goal-based trajectory analysis for unusual behaviour detection in intelligent surveillance
F. Tung, J.S. Zelek, and D.A. Clausi
Image and Vision Computing, vol. 29, pp. 230-240, 2011
Enabling scalable spectral clustering for image segmentation
F. Tung, A. Wong, and D.A. Clausi
Pattern Recognition, vol. 43, pp. 4069-4076, 2010
Efficient target recovery using STAGE for mean-shift tracking
F. Tung, J.S. Zelek, and D.A. Clausi
Canadian Conference on Computer and Robot Vision, 2009