Partager cette page :

A few challenges related to exploiting multimedia collections

le 3 octobre 2017

15h30 - 17h30

ENS Rennes, Salle du conseil
Plan d'accès

Intervention de Laurent Amsaleg, CR CNRS et  Guillaume Gravier, DR CNRS, équipe LinkMedia (IRISA, CNRS, Rennes), dans le cadre des séminaires du département Informatique et télécommunications.

Séminaire Informatique et télécommunications

Séminaire Informatique et télécommunications

Part 1: Structuring multimedia collections with links for media analytics

Media analytics refers to interactive exploration of multimedia collections to search for information, gain insight and knowledge on a topic of interest. Exploring large-scale collections requires an organization of the collection on top of the description of each item. We will review recent research at IRISA on the creation of links in media archives to offer graph-based navigation in large-scale collections, leveraging speech and natural language processing, statistical modeling, machine learning and graph theory.

Part 2: Image recognition and adversarial attacks

Recent research has shown that image recognition is vulnerable to adversarial attacks. By adding to the query image an imperceptible amount of adversarial noise, it is highly likely that image recognition can be tricked, possibly returning with a high similarity confidence an image that we, as humans, find extremely dissimilar. Such adversarial behaviors have also been observed in the context of machine learning and deep learning. We will discuss these issues.

Formation, Recherche - Valorisation
David Cachera & Luc Bougé

Mise à jour le 29 septembre 2017