 |
I am currently a computer science Ph.D. student at UC Berkeley, advised by Prof. Trevor Darrell. Before moving to Berkeley, I did my bachelors and masters at Tsinghua University, China, working in Prof. Changshui Zhang's research group. During the fall of 2009 I visited the National University of Singapore as a research engineer. I worked at the NEC Labs America as a research intern in the summer of 2011, and at Google Research in the summer of 2012. My office is at SDH 7th floor, and sometimes ICSI Rm 517. I do have an Email address: jiayq at berkeley dot edu. |
Research
My Ph.D. research is mainly focused on computer vision and machine learning, and my current interest is in learning better structures for image classification, and to explain human generalization behavior using visually grounded cogscience models.
Publications
Conference Papers
Y. Jia, O. Vinyals, T. Darrell. On Compact Codes for Spatially Pooled Features. ICML 2013 [PDF coming soon]
(Part of the work appeared in the ICLR workshop version:
O. Vinyals, Y. Jia, T. Darrell. Why size Matters: Feature Coding as Nystrom Sampling. ICLR 2013 [arXiv].)O. Vinyals, Y. Jia, L. Deng, T. Darrell. Learning with Recursive Perceptual Representations. NIPS 2012. [PDF]
S. Virtanen, Y. Jia, A. Klami, T. Darrell. Factorized Multi-modal Topic Model. UAI 2012 [PDF][Dataset]
Y. Jia, C. Huang, T. Darrell. Beyond Spatial Pyramids: Receptive Field Learning for Pooled Image Features. CVPR 2012 [PDF][slides]
Y. Jia, T. Darrell. Heavy-tailed Distances for Gradient Based Image Descriptors. NIPS 2011. [PDF] [Supplementary Material]
Y. Jia, M. Salzmann, T. Darrell. Learning Cross-modality Similarity for Multinomial Data. ICCV 2011. [PDF] [Dataset]
S. Karayev, A. Janoch, Y. Jia, J. Barron, M. Fritz, K. Saenko, T. Darrell. A Category-level 3-D Database: Putting the Kinect to Work. ICCV 2011 Workshop CDC4CV. [PDF] [Dataset]
K. Saenko, S. Karayev, Y. Jia, M. Fritz, J. Long, A. Janoch, A. Shyr, T. Darrell. Practical 3-D Object Detection Using Category and Instance-level Appearance Models. IROS 2011. [PDF]
Y. Jia, M. Salzmann, T. Darrell. Factorized Latent Spaces with Structured Sparsity. NIPS 2010. [PDF]
Y. Jia, S. Yan, C. Zhang. Semi-supervised Learning on Evolutionary Data. IJCAI 2009. [PDF]
Y. Jia, Z. Wang, C. Zhang. Distortion-Free Nonlinear Dimensionality Reduction. ECML 2008.
Y. Jia, C. Zhang. Instance-level Semi-supervised Multiple Instance Learning. AAAI 2008. [PDF]
Y. Jia, J. Wang, C. Zhang, X. Hua. Finding Image Exemplars Using Fast Sparse Affinity Propagation. ACM Multimedia 2008. [PDF]
J. Wang, Y. Jia, X. Hua, C. Zhang, L. Quan. Normalized Tree Partitioning for Image Segmentation. CVPR 2008. [PDF][matlab code]
F. Nie, S. Xiang, Y. Jia, C. Zhang, S. Yan. Trace Ratio Criterion for Feature Selection. AAAI 2008.
Y. Jia, J. Wang, C. Zhang, X. Hua. Augmented Tree Partitioning for Interactive Image Segmentation. ICIP 2008. [PDF]
Journal Articles
F. Nie, S. Xiang, Y. Jia, C. Zhang. Semi-supervised orthogonal discriminant analysis via label propagation. Pattern Recognition, 42:11, 2009. [PDF]
Y. Jia, F. Nie, C. Zhang. Trace Ratio Problem Revisited. IEEE Trans. Neural Networks, 20:4, 2009. [PDF]
Y. Jia, C. Zhang. Front-view Vehicle Detection by Markov Chain Monte Carlo Method. Pattern Recognition, 42:3, 2009.
Technical Reports
Y. Jia, J. Abbott, J. Austerweil, T. Griffiths, T. Darrell. Visually-Grounded Bayesian Word Learning. UC Berkeley EECS Tech Report. [PDF]
Y. Jia. Research on Regularization Based Semi-supervised Learning. Master Thesis, Tsinghua University, 2009. (in Chinese) [PDF]
Course Projects
Monocular Reconstruction of 2D Deformable Surfaces. CS 270: Computer Vision. [PDF]
Grounded Parsing of Object Attributes and Prepositions. CS 288: Statistical Natural Language Processing. [PDF]
Beanstalks: A General Purpose Job Queue for the ICSI Computer Vision Cluster. CS 262a: Advanced Topics in Computer Systems. [PDF]
Self-Organizing Sparse Codes. VS 265: Neural Computation. [PDF]
Software
Misc
I am co-organizing the weekly Machine Learning Tea at EECS Berkeley. ML Tea is an informal gathering for researchers interested in maching learning to present and discuss interesting techniques, applications and datasets. As always, there's food to seduce grad students.
In case you are wondering what I did before grad school: I started doing research on object recognition from the 1980s. No I didn't use a computer at that time.