David Mohlin
@MohlinD
Computer vision PhD student at KTH/RPL.
My paper "Probabilistic Regression with Huber Distributions" will be presented on BMVC tomorrow. In this paper we estimate mean-covariance parameterized probability distributions from using neural networks.
I am now presenting my paper at #BMVC2021 attendance for non-presenters seems to be free and is available online. bmvc2021-virtualconference.com/conference/pap…
I will present my NeurIPS poster for "Probabilistic Orientation Estimation with Matrix Fisher Distributions" at poster session 2, 18.00 today. Come check it out.
Our work got accepted at NeurIPS. The arxiv paper is still available at arxiv.org/abs/2006.09740 The code is public as well at github.com/Davmo049/Publi… There will be some minor differences between the NeurIPS paper and the one we submitted at arxiv.
Our work "Probabilistic orientation estimation with matrix Fisher distributions" is now publicly available. arxiv.org/abs/2006.09740 A challenge for estimating orientations is the presence of cavities in the output space. We remove this problem by using a probabilistic method.