Kangle Deng

I am a Phd candidate at the Robotics Institute of Carnegie Mellon University, where I'm fortunate to be co-advised by Deva Ramanan and Jun-Yan Zhu.

Prior to joining CMU, I obtained my B.S degree in 2020 from Peking University.

Email  /  CV  /  GitHub

profile photo
Research

I'm interested in Multimodal Perception, including Computer Vison and Audio Processing. I'm also interested in applications of Information Theory to Maching Learning. So far, my research mainly involves computer-aided creation.

Unsupervised Any-to-Many Audiovisual Synthesis via Exemplar Autoencoders
Kangle Deng, Aayush Bansal, Deva Ramanan
ArXiv
project page

Defined and addressed a new question of unsupervised audiovisual synthesis -- input the audio of a random individual and then output the talking-head video with audio in the style of another target speaker.

IRC-GAN: Introspective Recurrent Convolutional GAN for Text-to-video Generation
Kangle Deng*, Tianyi Fei*, Xin Huang, Yuxin Peng
IJCAI, 2019
bibtex

Application of Mutual Information to Text-to-video Generation.

Project
MiniC Compiler
Kangle Deng
Peking University, Fall 2019
project page

Compiler from miniC (a subset of C language) source code to RISC-V (majorly RV64I) executable.

1+N Fusion
Kangle Deng, Haoran Chen, Qingzhe Jin, Chang Wang
Peking University, Spring 2018
project page

Expanded the limited field of view of self-portraits using supporting background photos.

Teaching

Teaching Assistant:

  • Fall 2018, Introduction to Computer Systems, Peking University

This webpage is "stolen" from Jon Barron. Thanks to him!