Sequence Analysis and Modeling Lab
I gave a keynote on the Future of Diet and Nutrition Monitoring at Premier AI Conference in Shanghai on July 14, 2017. This was an event organized by Financial Times Chinese and the ZJ Innopark. A very interesting event with a mix of local and international speakers.
Some more photos from the media here.
Our paper about unsupervised probabilistic domain adaptation [1] for deep models (and other models too) has been accepted for ICCV’17:
@inproceedings{behnam17iccv,
added-at = {2017-07-18T17:26:03.000+0200},
author = {Gholami, Behnam and Rudovic, Ognjen and Pavlovic, Vladimir},
biburl = {https://www.bibsonomy.org/bibtex/29fd2aed9b960e71bf2472b5d70079060/vpavlovic},
booktitle = {Proc. IEEE International Conference Computer Vision},
interhash = {4a8c0ac9cfbd7b02e2d86ef7b5a289a0},
intrahash = {9fd2aed9b960e71bf2472b5d70079060},
keywords = {domain_adaptation myown unsupervised},
owner = {vladimir},
timestamp = {2017-07-18T18:21:19.000+0200},
title = {PUnDA: Probabilistic Unsupervised Domain Adaptation},
year = 2017
}
Congratulations to Behnam and Ognjen!
Our article on depth recovery using deformable object priors was accepted for publication in Journal of Visual Communication and Image Representation [1]:
@article{chen17jvcir,
added-at = {2017-07-18T17:26:03.000+0200},
author = {Chen, Chongyu and Pham, Hai Xuan and Pavlovic, Vladimir and Cai, Jianfei and Shi, Guangming and Gao, Yuefang},
biburl = {https://www.bibsonomy.org/bibtex/2d52164653eb6d2d7324656f9cbc20d3f/vpavlovic},
interhash = {14284536d8e03504dfb06b171c8598fe},
intrahash = {d52164653eb6d2d7324656f9cbc20d3f},
journal = {J. Visual Commun. Image Represent.},
keywords = {imported myown},
owner = {vladimir},
timestamp = {2017-07-18T18:07:32.000+0200},
title = {Using 3D Face Priors for Depth Recovery},
year = 2017
}
Congratulations!
We are excited to have three CVPR 2017 main conference papers accepted [1, 2, 3], as well as one workshop paper [4] :
@inproceedings{babagholami17cvpr,
added-at = {2017-07-18T17:26:03.000+0200},
author = {Babagholami, Behnam and Pavlovic, Vladimir},
biburl = {https://www.bibsonomy.org/bibtex/2e0a04837c7cd0540d2cd2f0aa442a097/vpavlovic},
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},
keywords = {cvpr17 myown subspace_clustering},
note = {Under review. 50\% contribution.},
timestamp = {2017-07-18T18:07:19.000+0200},
title = {Probabilistic Temporal Subspace Clustering},
year = 2017
}@inproceedings{walecki17cvpr,
added-at = {2017-07-18T17:26:03.000+0200},
author = {Walecki, Robert and Rudovic, Ognjen and Pavlovic, Vladimir and Schuller, Bjorn and Pantic, Maja},
biburl = {https://www.bibsonomy.org/bibtex/2fd5d11a30fb9f63aa76cfe46783b9bd8/vpavlovic},
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},
keywords = {cvpr17 deep_learning emotion_modeling expression_intensity_estimation myown ordinal_models},
timestamp = {2017-07-22T21:33:47.000+0200},
title = {Deep Structured Learning for Facial Expression Intensity Estimation},
year = 2017
}@inproceedings{sheng17cvpr,
added-at = {2017-07-18T17:26:03.000+0200},
author = {Sheng, Lu and Cai, Jianfei and Cham, Tat-Jen and Pavlovic, Vladimir and Ngan, King Ngi},
biburl = {https://www.bibsonomy.org/bibtex/2e18c6335e20344d4a11bceb8ec657b57/vpavlovic},
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},
keywords = {cvpr17 depth_camera face_modeling face_tracking myown},
note = {Under review. 25\% contribution.},
timestamp = {2017-07-18T18:07:32.000+0200},
title = {A Generative Model for Depth-based Robust 3D Facial Pose Tracking},
year = 2017
}@inproceedings{pham17cvpr,
added-at = {2017-07-18T17:26:03.000+0200},
author = {Pham, Hai and Pavlovic, Vladimir},
biburl = {https://www.bibsonomy.org/bibtex/2e6c72a93e19dd9fe1270b6d559534637/vpavlovic},
booktitle = {IEEE Int'l Conf. Computer Vision and Pattern Recognition - Workshop on Deep Affective Learning and Context Modeling},
interhash = {538627e583e79fae93dd8af09fcdc7eb},
intrahash = {e6c72a93e19dd9fe1270b6d559534637},
keywords = {deep_learning emotion_modeling face_animation myown speech_analysis},
owner = {vladimir},
timestamp = {2017-07-18T18:07:32.000+0200},
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!
Our article dealing with the problem of Ancient Coin Recognition was recently accepted for publication [1]:
![[doi]](http://seqamlab.com/wp-content/plugins/papercite/img/external.png){kind=small}
J. Kim and V. Pavlovic, “Discovering Characteristic Landmarks on Ancient Coins Using Convolutional Networks,” SPIE Journal of Electronic Imaging, 2017. @article{jongpil16spie,
added-at = {2017-07-18T17:26:03.000+0200},
author = {Kim, Jongpil and Pavlovic, Vladimir},
biburl = {https://www.bibsonomy.org/bibtex/20a2ffe339e53fea346b16501a76c5844/vpavlovic},
date-added = {2016-09-11 21:37:27 +0000},
date-modified = {2017-01-17 15:49:38 +0000},
doi = {10.1117/1.JEI.26.1.011018},
interhash = {0b5ba506800f82bb385df4391c8290d9},
intrahash = {0a2ffe339e53fea346b16501a76c5844},
journal = {{SPIE} Journal of Electronic Imaging},
keywords = {coin_analysis deep_learning myown},
note = {Accepted for publication. 50\% contribution.},
timestamp = {2017-07-18T18:07:19.000+0200},
title = {Discovering Characteristic Landmarks on Ancient Coins Using Convolutional Networks},
year = 2017
}
Congratulations to Jongpil!