WANG Yi-Qing

YQ

About Me:

I am a postdoctoral researcher in the Center for Vision, Cognition, Learning, and Autonomy (VCLA) at UCLA, under the supervision of Prof. Song-Chun Zhu. I obtained my Ph.D degree at Centre de Mathématiques et de Leurs Applications (CMLA), Ecole Normale Supérieure de Cachan, France under the supervision of Prof. Jean-Michel Morel. Prior to that, I received the diplôme d'ingénieur from Ecole Polytechnique, Palaiseau, France and B.E. from Fudan University, Shanghai, China respectively. My current research interest lies in statistical modeling and machine learning, with applications to computer vision.

Contact:

Email: yiqing.wang@cmla.ens-cachan.fr

Office: 9432 Boelter Hall, UCLA

Publications:

Y. Q. Wang, A. Trouvé, Y. Amit, B. Nadler  Detecting curved edges in noisy images in sublinear time   (Journal Of Mathematical Imaging and Vision, 2016). html.

Y. Q. Wang  A note on the size of denoising neural networks   (SIAM Journal Of Imaging Sciences, 2015).

Y. Q. Wang  A Multilayer Neural Network for Image Demosaicking   (IEEE International Conference on Image Processing, 2014). Demo link here.

Y. Q. Wang  An Analysis of the Viola-Jones Face Detection Algorithm   (Image Processing On Line, 2014).

Y. Q. Wang and J. M. Morel   Can a Single Image Denoising Neural Network Handle All Levels of Gaussian Noise?   (IEEE Signal Processing Letters, 2014). Code here.

Y. Q. Wang   EPLE: un algorithme d'inpainting performant   (in French, Symposium on Signal and Image Processing GRETSI, 2013). Code and demo link here.

Y. Q. Wang and J. M. Morel   SURE Guided Gaussian Mixture Image Denoising   (SIAM Journal of Imaging Sciences, 2013). Code and demo link here.

Code and datasets:

Download the training dataset (2.6G) used in my Viola-Jones face detector implementation.

Download the training dataset (505M) used in my neural demosaicing implementation.

Teaching:

Introduction à l'apprentissage statistique (TD 2013-2015)

Bayes Classifier, Perceptron and KKT Conditions

Excess Risk, Consistency and Histogram Rule

K Nearest Neighbors and its Consistency

Plug-In Rule and Maximum Likelihood Inference

Introduction to statistical inference and learning (2015-2016)

Syllabus Ex1 Ex2 Ex3 Ex4 Ex5 exam