Jianchao Yang
Research Scientist
Snapchat
Email: jyang29 [at] ifp.uiuc.edu, jcyangenator [at] gmail.com
CV | Google Scholar | LinkedIn

I am a Research Scienist at Snapchat located on Venice beach in Los Angeles. Before joining Snapchat, I was a Research Scientist at Adobe Research in San Jose, California. I got my M.S. and Ph.D. degrees from the ECE department of University of Illinois at Urbanan-Champaign (UIUC) in 2010 and 2011, both under supervision of Professor Thomas Huang at Beckman Institute. Before that, I received my Bachelor’s degree with honor in the EEIS department from University of Science and Technology of China (USTC) in 2006.

My research interests are in the broad area of computer vision, machine learning, and image processing. Specifically, I have extensive experience in the following research areas: object recognition and detection, facial analysis, deep learning, subspace learning, supervised and unsupervised learning, sparse coding and sparse representation, image and video super-resolution, denoising and deblurring.

News

• Contact me if you are interested in non-summer intern opportunities.
• Large-scale dataset on image emotion analysis published on AAAI 2016. Check it out .

Codes

CSCN code for image super-resolution. [Project ]
Test code for the algorithm proposed in “Deep networks for image super-resolution with sparse prior” ICCV 2015.

LLC matlab code for image classification. [Download ]
Example matlab code for the algorithm proposed in “Locality-constrained linear coding for image classification” CVPR 2010.

ScSPM matlab code for image classification. [Download ]
Example matlab code for the algorithm proposed in “Linear spatial pyramid matching uisng sparse coding for image classification” CVPR 2009.

ScSR matlab code for image super-resolution. [Download ]
Example matlab code for the algorithm proposed in “Image super-resolution via sparse representation” TIP 2010.

Selected Publications complete list

Cross-modality consistent regression for joint visual-textual sentiment analysis of social multimedia. [PDF ]
Quanzeng You, Jiebo Luo, Hailin Jin, Jianchao Yang.
ACM International Conference on Web Search and Data Mining (WSDM ), Feb. 2016

Building a large scale dataset for image emotion recognition: The fine print and the benchmark. [Project ]
Quanzeng You, Hailin Jin, Jianchao Yang, Jiebo Luo.
30th AAAI Conference on Artificial Intelligence (AAAI ), 2016.

Sparse coding and its applications in computer vision. [Link ]
Zhaowen Wang, Jianchao Yang, Haichao Zhang, Zhangyang Wang, Yingzhen Yang, Ding Liu, and Thomas Huang.
World Scientific. Dec. 2015, ISBN: 978-981-4725-04-0.

Human parsing with contextualized convolutional neural network. [PDF ]
Xiaodan Liang, Si Liu, Xiaohui Shen, Jianchao Yang, and Shuicheng Yan.
IEEE International Conference on Computer Vision (ICCV ), 2015.

Deep networks for image super-resolution with sparse prior. [PDF |Project ]
Zhaowen Wang, Ding Liu, Jianchao Yang, Wei Han, and Thomas Huang.
IEEE International Conference on Computer Vision (ICCV ), 2015.

DeepFont: Identify your font from an image. [PDF ]
Zhangyang Wang, Jianchao Yang, Hailin Jin, Eli Shechtman, Aseem Agarwala, Jonathan Brandt, Thomas Huang.

ACM International Conference on Multimedia (ACM MM ) full paper, 2015.

Joint visual-textual sentiment analysis with deep neural networks. [PDF ]
Quanzeng You, Jiebo Luo, Hailin Jin, Jianchao Yang.
ACM International Conference on Multimedia (ACM MM ) short, 2015.

Deep human parsing with active template regression. [PDF ]
Xiaodan Liang, Si Liu, Xiaohui Shen, Jianchao Yang, Luoqi Liu, Liang Lin, Shuicheng Yan.
IEEE Transactions on Pattern Analysis and Macine Intelligence (TPAMI ), Volume 37, Issue 12, Dec. 2015.

Learning super-resolution jointly from external and internal examples. [PDF ]
Zhangyang Wang, Yingzhen Yang, Zhaowen Wang, Shiyu Chang, Jianchao Yang, and Thomas Huang.
IEEE Transactions on Image Processing (TIP ), Volume 24, Number 11, Nov. 2015.

Image specific prior adaptation for image denoising. [PDF ]
Xin Lu, Zhe Lin, Jianchao Yang, Hailin Jin.
IEEE Transactions on Image Processing (TIP ), Volume 24, Issue 12, Aug. 2015.

Parsing based on parselets: A unified deformable mixture model for human parsing. [PDF ]
Jian Dong, Qiang Chen, Zhongyang Huang, Jianchao Yang, Shuicheng Yan.
IEEE Transactions on Pattern Analysis and Macine Intelligence (TPAMI ), Volume 38, Issue 1, April 2015.

Intra-frame deblurring by leveraging inter-frame camera motion. [PDF ]
Haichao Zhang, Jianchao Yang.
IEEE International Conference on Computer Vision and Pattern Recognition (CVPR ), 2015.

Fine-grained recognition without part annotation. [PDF ]
Jonathan Krause, Hailin Jin, Jianchao Yang, Li Fei-Fei.
IEEE International Conference on Computer Vision and Pattern Recognition (CVPR ), 2015.

Collaborative feature learning from social media. [PDF ]
Chen Fang, Hailin Jin, Jianchao Yang, Zhe Lin.
IEEE International Conference on Computer Vision and Pattern Recognition (CVPR ), 2015.

Matching-CNN meets KNN: Quasi-parametric human parsing. [PDF ]
Si Liu, Xiaodan Liang, Luoqi Liu, Xiaohui Shen, Jianchao Yang, Changsheng Xu, Liang Lin, Xiaochun Chao, Shuicheng Yan.
IEEE International Conference on Computer Vision and Pattern Recognition (CVPR ), 2015.

Image sentiment analysis using progressively trained and domain transferred deep networks. [PDF ]
Quanzeng You, Jiebo Luo, Hailin Jin, Jianchao Yang.
29th AAAI Conference on Artificial Intelligence (AAAI ), 2015.

Scale adaptive blind deblurring. [PDF ]
Haichao Zhang, Jianchao Yang, Lawrence Carin.
Advances in Neural Information Processing Systems (NIPS ), 2014.

RAPID: Rating pictorial aesthetics using deep learning. [PDF ]
Xin Lu, Zhe Lin, Hailin Jin, Jianchao Yang, James Z. Wang.
ACM Multimedia (ACM MM ) full paper, 2014.

Large-scale visual font recognition. [PDF ]
Guang Chen, Jianchao Yang, Hailin Jin, Jon Brandt, Eli Shechtman, Aseem Agarwala, Xu Han.
IEEE International Conference on Computer Vision and Pattern Recognition (CVPR ), 2014.

Investigating haze-relevant features in a learning framework for image dehazing. [PDF ]
Ketan Tang, Jianchao Yang, Jue Wang.
IEEE International Conference on Computer Vision and Pattern Recognition (CVPR ), 2014.

Towards unified human parsing and pose estimation. [PDF ]
Jian Dong, Qiang Chen, Xiaohui Shen, Jianchao Yang, Shuicheng Yan.
IEEE International Conference on Computer Vision and Pattern Recognition (CVPR ), 2014.

Non-local compressive sampling recovery. [PDF ]
Xianbiao Shu, Jianchao Yang, Narendra Ahuja.
IEEE International Conference on Computational Photography (ICCP ), 2014.

A max-margin perspective on sparse representation-based classification. [PDF ]
Zhaowen Wang, Jianchao Yang, Nasser Nasrabadi, and Thomas Huang.
IEEE International Conference on Computer Vision (ICCV ), 2013.

Text localization in natural images using stroke feature transform and text covariance descriptors. [PDF ]
Weilin Huang, Zhe Lin, Jianchao Yang, and Jue Wang.
IEEE International Conference on Computer Vision (ICCV ), 2013.

Probabilistic elastic part model for unsupervised face detector adaptation. [PDF ]
Haoxiang Li, Gang Hua, Zhe Lin, Jonathan Brandt, and Jianchao Yang.
IEEE International Conference on Computer Vision (ICCV ), 2013.

Fast image super-resolution based on in-place example regression. [PDF |Results ]
Jianchao Yang, Zhe Lin, and Scott Cohen.
IEEE Conference on Computer Vision and Pattern Recognition (CVPR ), 2013.

Probabilistic elastic matching for pose variant face verification. [PDF ]
Haoxiang Li, Gang Hua, Zhe Lin, Jonathan Brandt, and Jianchao Yang.
IEEE Conference on Computer Vision and Pattern Recognition (CVPR ), 2013.

Examplar-based face parsing. [PDF |Project ]
Brandon Smith, Li Zhang, Jonathan Brandt, Zhe Lin, and Jianchao Yang.
IEEE Conference on Computer Vision and Pattern Recognition (CVPR ), 2013.

Bilevel sparse coding for coupled feature spaces. [PDF ]
Jianchao Yang, Zhaowen Wang, Zhe Lin, Xianbiao Shu, and Thomas Huang.
IEEE Conference on Computer Vision and Pattern Recognition (CVPR ), 2012.

Learning L1-graph for high-dimenstional data analysis. [Link ]
Jianchao Yang, Bin Cheng, Shuicheng Yan, Yun Fu, and Thomas Huang.
In “Graph embedding for pattern analysis”, Springer, 2012, Yun Fu and Yunqian Ma (Editor).

Photo stream alignment and summarization for collaborative photo collection and sharing. [PDF ]
Jianchao Yang, Jiebo Luo, Jie Yu, and Thomas Huang.
IEEE Transactions on Multimedia (TMM ), vol. 14, issue 6, pages 1642-1651, 2012.

Coupled dictionary training for image super-resolution. [PDF ]
Jianchao Yang, Zhaowen Wang, Zhe Lin, and Thomas Huang.
IEEE Transactions on Image Processing (TIP ), vol. 21, issue 8, pages 3467-3478, 2012.

Close the loop: Joint blind image restoration and recognition with sparse representation prior. [PDF ]
Haichao Zhang, Jianchao Yang, Yanning Zhang, Nasser Nasrabadi, and Thomas Huang.
IEEE International Conference on Computer Vision (ICCV ), 2011. Best student paper award

Image super-resolution via sparse representation. [PDF |Project ]
Jianchao Yang, John Wright, Thomas Huang, and Yi Ma.
IEEE Transactions on Image Processing (TIP ), vol. 19, issue 11, 2010.

Image super-resolution: historical overview and future challenges. [PDF ]
Jianchao Yang and Thomas Huang.
In “Super-resoluton imaging”, CRC Press, 2010, Peyman Milanfar (Editor).

Learning with L1-graph for image analysis. [PDF ]
Bin Cheng, Jianchao Yang, Shuicheng Yan, and Thomas Huang.
IEEE Transactions on Image Processing (TIP ), vol. 19, no. 4, 2010.

Efficient highly over-complete sparse coding using a mixture model. [PDF ]
Jianchao Yang, Kai Yu, and Thomas Huang.
The 11th European Conference on Computer Vision (ECCV ), 2010.

Non-local kernel regression for image and video restoration. [PDF |Demo ]
Haichao Zhang, Jianchao Yang, Yanning Zhang, and Thomas Huang.
The 11th European Conference on Computer Vision (ECCV ), 2010.

Locality-constrained linear coding for image classification. [PDF |Project ]
Jinjun Wang, Jianchao Yang, Kai Yu, Fengjun Lv, and Thomas Huang.
IEEE Conference on Computer Vision and Pattern Recognition (CVPR ), 2010.

Supervised translation-invariant sparse coding. [PDF |Slides ] [Talk ]
Jianchao Yang, Kai Yu, and Thomas Huang.
IEEE Conference on Computer Vision and Pattern Recognition (CVPR ), 2010.

Linear spatial pyramid matching uisng sparse coding for image classification. [PDF |Project ]
Jianchao Yang, Kai Yu, Yihong Gong, and Thomas Huang.
IEEE Conference on Computer Vision and Pattern Recognition (CVPR ), 2009.

Ubiquitously supervised subspace learning. [PDF ]
Jianchao Yang, Shuicheng Yan, and Thomas Huang.
IEEE Transactions on Image Processing (TIP ), vol. 18, no. 2, 2009.

Image super-resolution as sparse representation of raw image patches. [PDF ]
Jianchao Yang, John Wright, Thomas Huang, and Yi Ma.
IEEE Conference on Computer Vision and Pattern Recognition (CVPR ), 2008.

Nonnegative graph embedding. [PDF |Slides ]
Jianchao Yang, Shuicheng Yan, Yun Fu, Xuelong Li, and Thomas Huang.
IEEE Conference on Computer Vision and Pattern Recognition (CVPR ), 2008.

Dissertations

Sparse modeling of high-dimensional data for learning and vision. [PDF ]
Jianchao Yang
Ph.D. dissertation, University of Illinois at Urbanan-Champaign, 2011.
Advisor: Prof. Thomas Huang

Image super-resolution via sparse representation. [PDF ]
Jianchao Yang
M.S. thesis, University of Illinois at Urbana-Champaign, 2010.
Advisor: Prof. Thomas Huang

Professional Activities

• Conference reviewer: CVPR, ICCV, ECCV, NIPS, SIGGRAPH, etc.
• Journal reviewer: TPAMI, IJCV, TOG, TIP, etc.