See the world with your eyes, and with your mind.
  research
  My Research interests
How computers can have high-level understanding from digital images or videos.
Input data is continuously used to extend the existing model's knowledge
Using multiple modalities to better understand human behavior

News

-> 2021 October I joined the Thoth team as a PhD student under the supervision of Karteek Alahari 🔥
-> 2021 September Funded by Facebook Reality Lab, my one-year project about Visually-asisted speech processing came to an happy ending. 👏

Publications

Preprints:

Kang, Zhiqi, Mostafa Sadeghi, and Radu Horaud. “Face Frontalization Based on Robustly Fitting a Deformable Shape Model to 3D Landmarks.” arXiv preprint arXiv:2010.13676 (2020).

Conference papers:

Kang, Zhiqi, Radu Horaud, and Mostafa Sadeghi. “Robust Face Frontalization For Visual Speech Recognition.” International Conference on Computer Vision Workshops. 2021.

Kang, Zhiqi, et al. “Understanding political communication styles in televised debates via body movements.” European Conference on Computer Vision Workshops. Springer, Cham, 2020.

Journal papers:

Community activities

I was the reviewer for the following conference:

> ACM Multimedia 2021