Welcome to my homepage. I am a graduate student at Department of Computer Science, School of Arts and Sciences, at Rutgers University advised by Professor Vladimir Pavlovic. I did a recent internship with Maja Pantic and Vladimir Pavlovic at Samsung Research AI Center (SRUK). Previously, I got my Master’s degree at Karlsruhe Institute of Technology advised by Professor Alexander Waibel and Professor Florian Metze, and received my B.E. at University of Duisburg-Essen, both with highest honor.
My research interests include computer vision, speech recognition, cognitive system, machine learning and deep learning.
Current Research Topics
Representation Learning, Automatic Facial Animation, Attention Model
Research Project:
- Bayes-Factor-VAE: Hierarchical Bayesian Deep Auto-Encoder Models for Factor Disentanglement.
[Bibtex]
@inproceedings{kim19iccv,
Address = {Seoul, Korea},
Author = {Minyoung Kim and Yuting Wang and Pritish Sahu and Vladimir Pavlovic},
Booktitle = {{IEEE} International Conference on Computer Vision, {ICCV}},
Date-Added = {2019-09-05 20:58:51 +0100},
Date-Modified = {2019-09-05 21:00:05 +0100},
Month = {October},
Title = {Bayes-Factor-{VAE}: Hierarchical {Bayesian} Deep Auto-Encoder Models for Factor Disentanglement},,
Year = {2019}
}
- Relevance Factor VAE: Learning and Identifying Disentangled Factors.
[Bibtex]
@article{kim2019relevance,
title = {Relevance Factor VAE: Learning and Identifying Disentangled Factors},
author = {Kim, Minyoung and Wang, Yuting and Sahu, Pritish and Pavlovic, Vladimir},
journal={arXiv preprint arXiv:1902.01568},
year = {2019}
}
- A Hybrid Generative Adversarial Model for Collaborative Filtering
- End-to-End Learning for 3D Facial Animation from Speech.
[Bibtex]
@inproceedings{Pham:2018:ELF:3242969.3243017,
author = {Pham, Hai Xuan and Wang, Yuting and Pavlovic, Vladimir},
title = {End-to-end Learning for 3D Facial Animation from Speech},
booktitle = {Proceedings of the 20th ACM International Conference on Multimodal Interaction},
series = {ICMI ’18},
year = {2018},
isbn = {978-1-4503-5692-3},
location = {Boulder, CO, USA},
pages = {361–365},
numpages = {5},
url = {http://doi.acm.org/10.1145/3242969.3243017},
doi = {10.1145/3242969.3243017},
acmid = {3243017},
publisher = {ACM},
address = {New York, NY, USA},
keywords = {deep learning, facial animation, speech-driven},
}
- Generative Adversarial Talking Head: Bringing Portraits to Life with a Weakly Supervised Neural Network.
[Bibtex]
article{pham2018generative,
title = {Generative adversarial talking head: Bringing portraits to life with a weakly supervised neural network},
author = {Pham, Hai X and Wang, Yuting and Pavlovic, Vladimir},
journal={arXiv preprint arXiv:1803.07716},
year = {2018}
}
- End-to-end Learning from Sketch to Facial Expression
Publications:
2019
- M. Kim, Y. Wang, P. Sahu, and V. Pavlovic, “Bayes-Factor-VAE: Hierarchical Bayesian Deep Auto-Encoder Models for Factor Disentanglement,” in IEEE International Conference on Computer Vision, ICCV, Seoul, Korea, 2019.
[BibTeX]@InProceedings{kim19iccv, author = {Minyoung Kim and Yuting Wang and Pritish Sahu and Vladimir Pavlovic}, booktitle = {{IEEE} International Conference on Computer Vision, {ICCV}}, title = {Bayes-Factor-{VAE}: Hierarchical {Bayesian} Deep Auto-Encoder Models for Factor Disentanglement}, year = {2019}, address = {Seoul, Korea}, month = oct, date-added = {2019-09-05 20:58:51 +0100}, date-modified = {2019-09-05 21:00:05 +0100}, } - M. Kim, Y. Wang, P. Sahu, and V. Pavlovic, “Relevance Factor VAE: Learning and Identifying Disentangled Factors,” CoRR, vol. abs/1902.01568, 2019.
[BibTeX]@article{kim19rfvae_arxiv, Author = {Minyoung Kim and Yuting Wang and Pritish Sahu and Vladimir Pavlovic}, Journal = {CoRR}, Title = {Relevance Factor {VAE:} Learning and Identifying Disentangled Factors}, Volume = {abs/1902.01568}, Year = {2019}}
2018
- H. X. Pham, Y. Wang, and V. Pavlovic, “End-to-end Learning for 3D Facial Animation from Speech,” in ICMI, 2018, p. 361–365. doi:10.1145/3242969.3243017
[BibTeX]@InProceedings{hai18icmi, author = {Hai Xuan Pham and Yuting Wang and Vladimir Pavlovic}, booktitle = {{ICMI}}, title = {End-to-end Learning for 3D Facial Animation from Speech}, year = {2018}, pages = {361--365}, publisher = {{ACM}}, doi = {10.1145/3242969.3243017}, } - H. X. Pham, Y. Wang, and V. Pavlovic, “Generative Adversarial Talking Head: Bringing Portraits to Life with a Weakly Supervised Neural Network,” CoRR, vol. abs/1803.07716, 2018.
[BibTeX]@article{hai18gath_arxiv, Author = {Hai Xuan Pham and Yuting Wang and Vladimir Pavlovic}, Journal = {CoRR}, Title = {Generative Adversarial Talking Head: Bringing Portraits to Life with a Weakly Supervised Neural Network}, Volume = {abs/1803.07716}, Year = {2018}}
2017
- H. X. Pham, Y. Wang, and V. Pavlovic, End-to-end Learning for 3D Facial Animation from Raw Waveforms of Speech, 2017.
[BibTeX] [Download PDF]@unpublished{pham18fg, Author = {Hai Xuan Pham and Yuting Wang and Vladimir Pavlovic}, Keywords = {emotions, face animation, speech}, Note = {under review}, Title = {End-to-end Learning for 3D Facial Animation from Raw Waveforms of Speech}, Url = {https://arxiv.org/abs/1710.00920}, Year = {2017}, Bdsk-Url-1 = {https://arxiv.org/abs/1710.00920}}
- H. X. Pham, Y. Wang, and V. Pavlovic, Generative Adversarial Talking Head: Bringing Portraits to Life with a Weakly Supervised Neural Network.
[BibTeX]@unpublished{hai19tac, Author = {Hai Xuan Pham and Yuting Wang and Vladimir Pavlovic}, Date-Added = {2019-09-05 21:05:51 +0100}, Date-Modified = {2019-09-09 16:39:27 -0400}, Note = {Under review}, Title = {Generative Adversarial Talking Head: Bringing Portraits to Life with a Weakly Supervised Neural Network}}
Teaching Assistant
- Introduction to Discrete Structures I (CS-205), Rutgers University, Instructor: Antonio Miranda, Fall 2017.
- Introduction to Discrete Structures II (CS-206), Rutgers University, Instructor: Eliane Traldi, Spring 2018.
- Data Structure (CS-112), Rutgers University, Instructor: Kevin Mc Inerney, Summer 2018.
- Introduction to Discrete Structures I (CS-205), Rutgers University, Instructor: Wes Cowan, Fall 2018
- Introduction to Artificial Intelligence (CS-440), Rutgers University, Instructor: Abdeslam Boularias, Fall 2019.