Seminars


autres années: 2016


The Upcoming Seminars in LIVIA in 2017 :


November 22, 2017 , Room: A-3600, time: 12:00
Jose Dolz Topic: Deep CNN ensembles and suggestive annotations for infant brain MRI segmentation.


Previous Talks:


November 8, 2017 , Room: A-3600, time: 12:00
Luiz Gustavo Topic: adversarial examples in deep neural networks.(Github Link) (Slides)
October 11, 2017 , Room: A-3600, time: 12:00
Karthik Gopinath Topic: A design for an automated Optical Coherence Tomography analysis system.(Slides)
September 12, 2017 , Room: A-1424, time: 14:00
Prof. Marco Loog (Delft University) Topic: Improvement Guarantees for Semi-Supervised Learning.
September 8, 2017 , Room: A-3600, time: 14:00
Prof. Jing Yuan (Xidian University, China) Topic: High-Performance Dual Decomposition and Optimization Methods with Applications to Image Analysis.
July 19, 2017 , Room: A-3600, time: 12:00
Prof. Kuldeep Kumar, PhD student (ETS) Topic: Fiberprint: a subject fingerprint based on sparse code pooling for white matter fiber analysis.
June 26, 2017 (Monday) , Room: A-1424, time: 14:00
Prof. Pierre-Marc Jodoin,(University of Sherbrooke) Topic: Recent advances at the VITALab : solving video analytic and medical imaging problems trough deep learning methods.
June 7, 2017 (Wednesday) , Room:
Dr. Jose Dolz
(ETS)                                   
Topic: Segmentation of Medical Images via Deep Learning Techniques: Current State-Of-The-Art and Perspectives. (Slides)
May 18, 2017 (Thursday) , Room: A-1170
Prof. Yuri Boykov, (University of Western Ontario) Topic: Kernel Clustering meets Markov Random Fields.
May 18, 2017 (Thursday) , Room: A-1170
Prof. Prof. Olga Veskler,
(University of Western Ontario)
Topic: Adaptive and Move Making Auxiliary Cuts for Binary Pairwise Energies.
May 10, 2017 (Wednesday) , Room: A-1424
Dr. Albert Gordo,
(Computer Vision Group, Xerox Research Centre Europe)
Topic: Learning deep image representations for visual search.
April 19, 2017 (Wednesday) , Room: A-1424
Prof. Marco Pedersoli
(ETS)
Topic: Weakly Supervised Models for Visual Recognition. (Slides)