M
Mathieu Salzmann
Researcher at École Polytechnique Fédérale de Lausanne
Publications - 337
Citations - 14350
Mathieu Salzmann is an academic researcher from École Polytechnique Fédérale de Lausanne. The author has contributed to research in topics: Computer science & Pose. The author has an hindex of 54, co-authored 298 publications receiving 10961 citations. Previous affiliations of Mathieu Salzmann include Toyota & Australian National University.
Papers
More filters
Journal ArticleDOI
Beyond Sharing Weights for Deep Domain Adaptation
TL;DR: This work introduces a two-stream architecture, where one operates in the source domain and the other in the target domain, and demonstrates that this both yields higher accuracy than state-of-the-art methods on several object recognition and detection tasks and consistently outperforms networks with shared weights in both supervised and unsupervised settings.
Proceedings ArticleDOI
Unsupervised Domain Adaptation by Domain Invariant Projection
Mahsa Baktashmotlagh,Mahsa Baktashmotlagh,Mehrtash Harandi,Mehrtash Harandi,Brian C. Lovell,Mathieu Salzmann,Mathieu Salzmann +6 more
TL;DR: This paper learns a projection of the data to a low-dimensional latent space where the distance between the empirical distributions of the source and target examples is minimized and demonstrates the effectiveness of the approach on the task of visual object recognition.
Proceedings ArticleDOI
Learning to Find Good Correspondences
TL;DR: In this paper, a multi-layer perceptron operating on pixel coordinates rather than directly on the image is proposed to learn to find good correspondences for wide-baseline stereo.
Proceedings ArticleDOI
Discrete-Continuous Depth Estimation from a Single Image
TL;DR: This paper forms monocular depth estimation as a discrete-continuous optimization problem, where the continuous variables encode the depth of the superpixels in the input image, and the discrete ones represent relationships between neighboring superPixels.
Proceedings ArticleDOI
Context-Aware Crowd Counting
TL;DR: In this article, an end-to-end trainable deep architecture that combines features obtained using multiple receptive field sizes and learns the importance of each such feature at each image location is proposed.