HCI Logo
Heidelberg University Logo
IWR Logo

Publications

Export 8 results:
Author Title [ Type(Asc)] Year
Filters: Author is Kandemir, M  [Clear All Filters]
Unpublished
M. Kandemir, Agkül, A., Haußmann, M., and Ünal, G., “Evidential Turing Processes”. arXiv preprint, 2021.
Conference Proceedings
M. Kandemir, Haußmann, M., Diego, F., Rajamani, K., van der Laak, J., and Hamprecht, F. A., “Variational weakly-supervised Gaussian processes”, BMVC. Proceedings. 2016.PDF icon Technical Report (3.28 MB)
M. Haußmann, Hamprecht, F. A., and Kandemir, M., “Variational Bayesian Multiple Instance Learning with Gaussian Processes”, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). pp. 6570-6579, 2017.PDF icon Technical Report (1.29 MB)
M. Haußmann, Gerwinn, S., Look, A., Rakitsch, B., and Kandemir, M., “Learning Partially Known Stochastic Dynamics with Empirical PAC Bayes”, International Conference on Artificial Intelligence and Statistics , vol. PMLR 130. pp. 478-486, 2021.
M. von Borstel, Kandemir, M., Schmidt, P., Rao, M., Rajamani, K., and Hamprecht, F. A., “Gaussian process density counting from weak supervision”, ECCV. Proceedings, vol. LNCS 9905. Springer, pp. 365-380 , 2016.PDF icon Technical Report (1.71 MB)
M. Kandemir and Hamprecht, F. A., “The Deep Feed-Forward Gaussian Process: An Effective Generalization to Covariance Priors”, NIPS. Proceedings, vol. 44. pp. 145-159, 2015.PDF icon Supplementary Material (223.39 KB)PDF icon Technical Report (2.58 MB)
M. Haußmann, Gerwinn, S., and Kandemir, M., “Bayesian Evidential Deep Learning with PAC Regularization ”, 3rd Symposium on Advances in Approximate Bayesian Inference . 2020.
Conference Paper
M. Kandemir, Rubio, J. C., Schmidt, U., Wojek, C., Welbl, J., Ommer, B., and Hamprecht, F. A., “Event Detection by Feature Unpredictability in Phase-Contrast Videos of Cell Cultures”, in Medical Image Computing and Computer-Assisted Intervention, 2014, p. 154--161.PDF icon Technical Report (2 MB)