This year’s PhD seminars concluded with an anniversary event that marked both the 2 years since their creation and the end of the Digital Health, Biology and Earth chapter. Program 14:00 Event opening by Denis Talay and Gérard Giraudon 14:30 2 Years of Phd Seminars: Key numbers by Konstantinos Mavreas…
Chairman Dimitra Politaki – NEO Speaker: Professor Nelly Litvak, University of Twente Talk 1 Title: Story-telling Abstract: When writing a paper or a grant proposal you will often hear `high-level’ advice such as: `write easier’, `make it crystal clear’, `explain what is new’, `make it exciting’. I will explain two hands-on…
| Monday | Tuesday | Wednesday | Thursday | Friday | Saturday | Sunday |
|---|---|---|---|---|---|---|
February 25, 20199:00 am: Le Monde des Mathématiques Industrielles (MOMI2019)9:00 am: Le Monde des Mathématiques Industrielles (MOMI2019)February 25, 2019 – |
February 26, 20199:00 am: Le Monde des Mathématiques Industrielles (MOMI2019)9:00 am: Le Monde des Mathématiques Industrielles (MOMI2019)February 26, 2019 – |
February 27, 2019 | February 28, 2019 | March 1, 2019 | March 2, 2019 | March 3, 2019 |
| March 4, 2019 | March 5, 2019 | March 6, 2019 | March 7, 2019 | March 8, 2019 | March 9, 2019 | March 10, 2019 |
| March 11, 2019 | March 12, 2019 | March 13, 2019 | March 14, 2019 | March 15, 2019 | March 16, 2019 | March 17, 2019 |
March 18, 20192:00 pm: PhD Seminars VIII2:00 pm: PhD Seminars VIIIMarch 18, 2019 – Talk 1
Nicolas GIRARD (TITANE) Title Aligning and Updating Building Maps with Aerial Images by Multi-Task, Multi-Resolution Deep Learning Abstract A large part of the world is already covered by maps of buildings. However when a new image of an already covered area is captured, it does not align perfectly with the existing map, due to a change of capture conditions, and errors in the map data. Those deformations can only be partially corrected, which leads to misalignments. Leveraging multi-task learning, our model aligns the existing buildings to the new image through a displacement output, and detects new buildings that do not appear in the map through a segmentation output. We also apply our method to buildings height estimation, by aligning to a pair of stereo images. An extension of our work in the noisy-supervision setting allows for the alignement of misaligned building maps without the use of perfect ground truth data for training. Talk 2
|
March 19, 2019 | March 20, 2019 | March 21, 2019 | March 22, 2019 | March 23, 2019 | March 24, 2019 |
| March 25, 2019 | March 26, 2019 | March 27, 2019 | March 28, 2019 | March 29, 2019 | March 30, 2019 | March 31, 2019 |
