Human Behavior Understanding by Prof. Mohamed Daoudi

The use of Riemannian geometry to model various computer vision problems has recently received renewed interest. The advantages of geometric thinking can be understood by the fact that in many applications the data naturally lives in nonlinear manifolds, so distances and similarity measures computed by considering the geometry of the data space naturally result in better and more accurate modeling.

Martedì 27 luglio, ore 11:00, aula Anfiteatro, edificio Ex-Farmacologia, viale Morgagni 65. Prof. Mohamed Daoudi, IMT Lille DOUAI, CRIStAL (UMR CNRS) “Human Behavior Understanding” lecture.

Furthermore, in the last decade, deep learning approaches (e.g., Convolutional Neural Networks (CNN) and Generative Adversarial Network (GAN)) have achieved unprecedented performance in computer vision. Despite these results, research on deep learning techniques has so far mainly focused on Euclidean data.

In this talk, based on our recent results, I will show that putting together the geometry and deep learning can lead to elegant solutions to various problems in computer vision.

Lecturer: Mohamed Daoudi is a professor of Computer Science at IMT Lille Douai and a leader of Image group at CRIStAL (UMR CNRS 9189). His research interests include pattern recognition and computer vision and he is the author of over 150 scientific publications that have appeared in the most distinguished international journals and conference proceedings.

He is the editor of several books including “3D Face Modeling, Analysis and Recognition” Wiley 2013 and “3D Object Processing: Compression, Indexing and Watermarking” Wiley 2008. He is a Senior Member of IEEE and a Fellow of IAPR. He is an Associate editor of Image and Vision Computing Journal (since 2016), IEEE Transactions on Multimedia (since 2018) and Journal of Imaging (since 2018). He has been Guest Editor of several Special Issues on 3D Humans Analysis and Recognition, face and gesture recognition, and manifolds for computer vision on some of the most prestigious scientific journals.

He has also been a member of the Scientific Program Committee of many international conferences in the fields of computer vision and artificial intelligence. He has been General Chair of the 14th IEEE International Conference on Automatic Face and Gesture Recognition, IEEE FG 2019, and of the International Conference on Intelligent Systems and Computer Vision 2017, ISCV 2017, and of several other international workshops.

(*) La capienza COVID dell’aula anfiteatro è limitata a 28 posti.

Sarà possibile partecipare al seminario da remoto collegandosi all’indirizzo:
https://unifirenze.webex.com/unifirenze/j.php?MTID=m4029d074fb747324ddbdc6c5c4489f95

Numero riunione: 121 003 7683
Password: MfCeU3HTJ32
Chiave organizzatore: 459981

Accedi tramite sistema video
Chiama 1210037683@unifirenze.webex.com
È possibile anche chiamare 62.109.219.4 e immettere il numero della riunione.

Accedi per telefono
+39-069-974-8087 Italy Toll
390230410440 Italy Toll 2
Codice di accesso: 121 003 7683

Sho Takahashi

Lecture by Sho Takahashi

Video analysis for sports understanding

Stan Sclaroff

Lecture by Stan Sclaroff

Attention, Capabilities of Humans, Algorithms in Vision

Yahoo YStar!

donation of 98 servers by Yahoo YSTAR

My Kieu, Andrew D. Bagdanov, Marco Bertini, Alberto del Bimbo, Task-conditioned Domain Adaptation for Pedestrian Detection in Thermal Imagery

ECCV 2020 Paper

Domain Adaptation for Pedestrian Detection