ICCV 2017 – Wrap Up

Last week was the time for ICCV 2017 in Venice, Italy.  Setting aside my personal indifference to Venice (overcrowded and overpriced, uninspiring food),  ICCV was an interesting meeting.  It took place on Lido, at the same venue as the Venice Film Festival.  It was certainly a more appealing location to me personally, but a bit of a way from San Marco and the tourist Venice.

The conference itself was, well, a mixed bag.  Plenty of deep block shuffling works.  About 3000 attendees is the number I heard.

We presented our work “PUnDA: Probabilistic Unsupervised Domain Adaptation for Knowledge Transfer Across Visual Categories” [1]. It shows that it is not always necessary to have end-to-end learning if the transfer model is properly constructed.   As the luck has it, I had to reshuffle the schedule so the poster was both on Wednesday and Thursday (thanks to Robert Walecki, who help with the poster.)  You can find a copy of the poster below.

[1] B. Gholami, O. Rudovic, and V. Pavlovic, “PUnDA: Probabilistic Unsupervised Domain Adaptation,” in Proc. IEEE International Conference Computer Vision, 2017.
[Bibtex]
@inproceedings{behnam17iccv,
author = {Gholami, Behnam and Rudovic, Ognjen and Pavlovic, Vladimir},
booktitle = {Proc. IEEE International Conference Computer Vision},
interhash = {4a8c0ac9cfbd7b02e2d86ef7b5a289a0},
intrahash = {9fd2aed9b960e71bf2472b5d70079060},
owner = {vladimir},
title = {PUnDA: Probabilistic Unsupervised Domain Adaptation},
year = 2017
}

“Unsupervised Domain Adaptation with Copula Models” presented at MLSP’17

Our paper “Unsupervised Domain Adaptation with Copula Models”[1] was presented this week at the IEEE Int’l Workshop on Machine Learning for Signal Processing in Tokyo, Japan.

It was an exciting meeting; unlike the now mega-conferences of CVPR and NIPS kind, MLSP is still refreshingly small.  There were several outstanding tutorials and keynotes by Kenji Fukumizu, Shun-ichi Amari, and Yee Whye Teh, with limited emphasis on “deep.”  Well organized!

Then, there was Tokyo itself.  Always a pleasure to visit.

References

[1] C. D. Tran, O. Rudovic, and V. Pavlovic, “Unsupervised domain adaptation with copula models,” in IEEE Int’l Conf. Machine Learning for Signal Processing (MLSP), 2017.
[Bibtex]
@InProceedings{tran17mlsp,
author = {Cuong D. Tran and Ognjen Rudovic and Vladimir Pavlovic},
title = {Unsupervised domain adaptation with copula models},
booktitle = {IEEE Int’l Conf. Machine Learning for Signal Processing (MLSP)},
year = {2017},
note = {33\% contribution.},
date-added = {2017-01-17 15:43:46 +0000},
date-modified = {2017-01-17 15:45:08 +0000},
keywords = {domain adaptation, mlsp17},
}

CVPR 2017 – Wrap Up

It was quite exciting to attend the largest CVPR ever – almost 5000 attendees.  Having it in a beautiful location made it even more appealing.

Thanks to my students and colleagues who made the work we presented at CVPR possible.

Joint work with Imperial College and MIT on using copula models for joint facial AU estimation.
Joint NTU Singapore – Rutgers work on generative models for robust 3D face pose estimation
Break time at Waikiki beach
Hai presenting his work at the 1st Int’l Workshop on Deep Affective Learning and Context Modeling

ICCV 2017

Our paper about unsupervised probabilistic domain adaptation [1] for deep models (and other models too) has been accepted for ICCV’17:

[1] B. Gholami, O. Rudovic, and V. Pavlovic, “PUnDA: Probabilistic Unsupervised Domain Adaptation,” in Proc. IEEE International Conference Computer Vision, 2017.
[Bibtex]
@inproceedings{behnam17iccv,
author = {Gholami, Behnam and Rudovic, Ognjen and Pavlovic, Vladimir},
booktitle = {Proc. IEEE International Conference Computer Vision},
interhash = {4a8c0ac9cfbd7b02e2d86ef7b5a289a0},
intrahash = {9fd2aed9b960e71bf2472b5d70079060},
owner = {vladimir},
title = {PUnDA: Probabilistic Unsupervised Domain Adaptation},
year = 2017
}

Congratulations to Behnam and Ognjen!

CVPR 2017

 We are excited to have three CVPR 2017 main conference papers accepted [1, 2, 3], as well as one workshop paper [4] :

[1] B. Babagholami and V. Pavlovic, “Probabilistic Temporal Subspace Clustering,” in IEEE Int’l Conf. Computer Vision and Pattern Recognition, 2017.
[Bibtex]
@inproceedings{babagholami17cvpr,
author = {Babagholami, Behnam and Pavlovic, Vladimir},
booktitle = {IEEE Int'l Conf. Computer Vision and Pattern Recognition},
date-added = {2017-01-17 15:43:46 +0000},
date-modified = {2017-01-17 15:45:08 +0000},
interhash = {92906adf52c283061c4f06eaac54aeca},
intrahash = {e0a04837c7cd0540d2cd2f0aa442a097},
note = {Under review. 50\% contribution.},
title = {Probabilistic Temporal Subspace Clustering},
year = 2017
}
[2] R. Walecki, O. Rudovic, V. Pavlovic, B. Schuller, and M. Pantic, “Deep Structured Learning for Facial Expression Intensity Estimation,” in IEEE Int’l Conf. Computer Vision and Pattern Recognition, 2017.
[Bibtex]
@inproceedings{walecki17cvpr,
author = {Walecki, Robert and Rudovic, Ognjen and Pavlovic, Vladimir and Schuller, Bjorn and Pantic, Maja},
booktitle = {IEEE Int'l Conf. Computer Vision and Pattern Recognition},
date-added = {2017-01-17 15:41:28 +0000},
date-modified = {2017-01-17 15:43:23 +0000},
interhash = {956179029a34e1c71fc4b94fb1a90ee8},
intrahash = {fd5d11a30fb9f63aa76cfe46783b9bd8},
title = {Deep Structured Learning for Facial Expression Intensity Estimation},
year = 2017
}
[3] L. Sheng, J. Cai, T. Cham, V. Pavlovic, and K. N. Ngan, “A Generative Model for Depth-based Robust 3D Facial Pose Tracking,” in IEEE Int’l Conf. Computer Vision and Pattern Recognition, 2017.
[Bibtex]
@inproceedings{sheng17cvpr,
author = {Sheng, Lu and Cai, Jianfei and Cham, Tat-Jen and Pavlovic, Vladimir and Ngan, King Ngi},
booktitle = {IEEE Int'l Conf. Computer Vision and Pattern Recognition},
date-added = {2017-01-17 15:45:33 +0000},
date-modified = {2017-01-17 15:46:47 +0000},
interhash = {112c6e22dda03c3d485b79595d210af1},
intrahash = {e18c6335e20344d4a11bceb8ec657b57},
note = {Under review. 25\% contribution.},
title = {A Generative Model for Depth-based Robust 3D Facial Pose Tracking},
year = 2017
}
[4] H. Pham and V. Pavlovic, “Speech-driven 3D Facial Animation with Implicit Emotional Awareness: A Deep Learning Approach,” in IEEE Int’l Conf. Computer Vision and Pattern Recognition – Workshop on Deep Affective Learning and Context Modeling, 2017.
[Bibtex]
@inproceedings{pham17cvpr,
author = {Pham, Hai and Pavlovic, Vladimir},
booktitle = {IEEE Int'l Conf. Computer Vision and Pattern Recognition - Workshop on Deep Affective Learning and Context Modeling},
interhash = {538627e583e79fae93dd8af09fcdc7eb},
intrahash = {e6c72a93e19dd9fe1270b6d559534637},
owner = {vladimir},
title = {Speech-driven 3D Facial Animation with Implicit Emotional Awareness: A Deep Learning Approach},
year = 2017
}

 

Go to our Research page to find out more.

Congratulations to all!