Visual Information Processing and Learning

Shishi Qiao

Grade: 2014 doctor candidate

Mentor: Xilin Chen

Research group: Scene Understanding

Research area: Video Face Retrieval/Recognition, Manifold Learning; Hierarchical Image Understanding, esp. for Image to Image Translation and Scene Image Generation

Hi, there! Thank you for visiting my homepage. I am currently a Ph.D candidate working with Professor Xilin Chen and Professor Ruiping Wang in Visual Information Processing and Learning Laboratory (VIPL), Institute of Computing Technology (ICT), Chinese Academy of Sciences (CAS). In my first two years, I focused on the problem of video based face retrieval and recognition. After that, I am quite interested in the generative models. Now, I am studying how to make the machine to understand objects and their relationships with the generative adversarial nets (GANs). If you are also interested in this area, please feel free to contact me for discussions.

Experience

Educational experience

2010~2014, Bachelor. Computer Science and Techonology, Harbin Institute of Techonology (HIT).
2014~now, Ph.D. candidate in Computer Vision, Visual Information Processing and Learning Laboratory (VIPL), Institute of Computing Technology

Research content

1. Object disentanglement learning

Interpretable deep feature learning, image to image translation with disentanglement, scene image generation

2. Video face retrieval

Deep networks with manifold modeling

Book or Paper

Papers

Shishi Qiao, Ruiping Wang, Shiguang Shan, Xilin Chen. Deep Video Code for Efficient Face Video Retrieval. In ACCV 2016.

Shishi Qiao, Ruiping Wang, Shiguang Shan, Xilin Chen. Deep Video Code for Efficient Face Video Retrieval. In TMM (under review).

Shishi Qiao, Ruiping Wang, Shiguang Shan, Xilin Chen. Deep Heterogeneous Hashing for Face Video Retrieval. In TIP(under review).

Two image generation works are under progress