What about me?

New to Statistics!

UCLA Statistics is great! Love it!

ACM Honor Class

Aenean ornare velit lacus, ac varius enim lorem ullamcorper dolore. Proin aliquam facilisis ante interdum. Sed nulla amet lorem feugiat tempus aliquam.

Lived in Shanghai, until...

I spent my first 20 year in Shanghai.

Maybe a photographer?

Aenean ornare velit lacus, ac varius enim lorem ullamcorper dolore. Proin aliquam facilisis ante interdum. Sed nulla amet lorem feugiat tempus aliquam.

Selected Project

Energy-based generative ConvNet on Inverse Reinforcement Learning

Inverse optimal control solves the problem of infering the cost function of a state-control pair from large number of expert trajectories, with the objective to perform ideal control based on the explicit cost function learned. We introduce energy-based generative model to estimate the cost function, and use Langevin Dynamic, a Monte Carlo based sampling algorithm, to directly sample the full trajectory.

Joint Face Detection and Alignment via Cascaded Compositional Learning

This work is based on "Joint cascade face detection and alignment" and "Unconstrained Face Alignment via Cascaded Compositional Learning". We aim to provide domain partition on the Joint cascade face detection and alignment method.

Generative Hierarchical Structure Learning of Sparse FRAME Models

This paper proposes a framework for generative learning of hierarchical structure of visual objects, based on training hierarchical random field models. The resulting model, which we call structured sparse FRAME model, is a straightforward variation on decomposing the original sparse FRAME model into multiple parts that are allowed to shift their locations, orientations and scales, so that the resulting model becomes a reconfigurable template.

Learning Generative ConvNet with Continuous Latent Factors

This paper proposes an alternating back-propagation algorithm for learning the generator network model. The model is a non-linear generalization of factor analysis. In this model, the mapping from the latent factors to the observed vector is parametrized by a convolutional neural network. The alternating back-propagation algorithm iterates between the following two steps: (1) Inferential back-propagation, which infers the latent factors by Langevin dynamics or gradient descent. (2) Learning back-propagation, which updates the parameters given the inferred latent factors by gradient descent.

Interactive Image Search for Clothing Recommendation

This paper proposes a novel approach to meet users' multi-dimensional requirements in clothing image retrieval.We propose the Hybrid Topic (HT) model to learn the intricate semantic representation of the descriptors above. The model provides an effective multi-dimensional representation of clothes and is able to perform automatic image annotation by probabilistic reasoning from image search. Furthermore, we develop a demand-adaptive retrieval strategy which refines users' specific requirements and removes users' unwanted features. Our experiments show that the HT method significantly outperforms the deep neural network methods.

Large-scale image retrieval competition

This is a competition hold by Alibaba. The goal is to output the picture with the most similarity by the given picture. The database is a million web pictures. There are three part for our model. They are saliency detection, CNN classification and text matching. I am in charge of saliency detection and classification. Our team ranked in the top 16 in the competition(Over 2000 teams).