I am working with Greg Mori at Simon Fraser University. I received the Ph.D. degree in computer science from the Sorbonne Universités. I was advised by Matthieu Cord and Nicolas Thome at the LIP6 Lab (UPMC Paris 6 / Sorbonne Universités).
Hi! I'm Thibaut Durand, a postdoctoral researcher in Computer Vision and Machine Learning.
Recent news
2018
- May I received the PhD prize 2017 from the French association in pattern recognition and interpretation (AFRIF)
- March Our TNNLS paper SyMIL: MinMax Latent SVM for Weakly Labeled Data, with N. Thome and M. Cord accepted!
- Feb 14 Talk on negative evidence pooling at the DeepVision workshop
- Jan I moved to the SFU Vision and Media Lab
- Jan Our TPAMI paper Negative Evidence for Deep Latent Structured Models, with N. Thome and M. Cord accepted!
Research
My primary research interests are in the fields of computer vision and machine learning. I work on weakly supervised learning and deep learning for visual recognition (object recognition, scene classification, action classification, image segmentation).
Recent publications
Exploiting Negative Evidence for Deep Latent Structured Models
IEEE Transactions on Pattern Analysis and Machine Intelligence (2018)
author = {Durand, Thibaut and Thome, Nicolas and Cord, Matthieu},
title = {{Exploiting Negative Evidence for Deep Latent Structured Models}},
booktitle = {IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)},
year = {2018}
}
WILDCAT: Weakly Supervised Learning of Deep ConvNets for Image Classification, Pointwise Localization and Segmentation
IEEE Conference on Computer Vision and Pattern Recognition (2017) Honolulu, Hawaii
Paper Project page Supplementary Code
author = {Durand, Thibaut and Mordan, Taylor and Thome, Nicolas and Cord, Matthieu},
title = {{WILDCAT: Weakly Supervised Learning of Deep ConvNets for Image Classification, Pointwise Localization and Segmentation}},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
year = {2017}
}
WELDON: Weakly Supervised Learning of Deep Convolutional Neural Networks
IEEE Conference on Computer Vision and Pattern Recognition (2016) Las Vegas, USA
Paper Project page Supplementary Poster Code
author = {Durand, Thibaut and Thome, Nicolas and Cord, Matthieu},
title = {{WELDON: Weakly Supervised Learning of Deep Convolutional Neural Networks}},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
year = {2016}
}
MANTRA: Minimum Maximum Latent Structural SVM for Image Classification and Ranking
IEEE International Conference on Computer Vision (2015) Santiago, Chile
Paper Project page Supplementary Poster Code
Author = {Thibaut Durand and Nicolas Thome and Matthieu Cord},
Title = {{MANTRA: Minimum Maximum Latent Structural SVM for Image Classification and Ranking}},
booktitle = {IEEE International Conference on Computer Vision (ICCV)},
Year = {2015}
}
Contact
TASC1 8000
8888 University Drive
Burnaby, BC
CANADA V5A 1S6