Israel-Dejene Gebru, Xavier Alameda-Pineda, Florence Forbes and Radu Horaud
We recently got a paper accepted at TPAMI!
We had this crazy idea of mixture models that are trained with weighted-data. Imagine you want to train a GMM, and each data point comes with a weight denoting the relevance of the data point for the model.We also explored the case in which this external relevance information is taken into account under the form of a prior. This is useful in cases where the external information is inaccurate.
You are more than welcome to take a look at the preprint [1].
References
- I. Gebru, X. Alameda-Pineda, F. Forbes, and R. Horaud, “EM algorithms for weighted-data clustering with application to audio-visual scene analysis,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 38, iss. 12, pp. 2402-2415, 2016. [ bib pdf code data arxiv ]
@article{Gebru-TPAMI-2016, title = {{EM} algorithms for weighted-data clustering with application to audio-visual scene analysis}, author = {Israel-Dejene Gebru and Xavier Alameda-Pineda and Florence Forbes and Radu Horaud}, journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence}, year={2016}, volume={38}, number={12}, pages={2402-2415}, url = {http://arxiv.org/abs/1509.01509}, arxiv = {http://arxiv.org/abs/1509.01509}, doi={10.1109/TPAMI.2016.2522425}, soft={http://perception.inrialpes.fr/people/Gebru/code/WD-EM.zip}, data={https://team.inria.fr/perception/avtrack1/}, pdf={http://xavirema.eu/wp-content/papercite-data/pdf/Gebru-TPAMI-2016.pdf} }