Discover the new publications of 3IA Côte d'Azur chairholders and students.
> Pierre Alliez
A kinematic-geometric model based on ankles’ depth trajectory in frontal plane for gait analysis using a single RGB-D camera
New publication: A collaboration between Inria, Lamhess (Laboratoire Motricité Humaine Expertise Sport Santé ) and Ekinnox startup, published in the Journal of Biomechanics.
Learn more
> Fabien Gandon
Interoperable AI: Evolutionary Race Towards Sustainable Knowledge Sharing
The advancement and deployment of artificial intelligent agents brought numerous benefits in knowledge and data gathering and processing. However, one of the key challenges is the interoperability of these AI agents as they currently mostly run in silos. We performed a simulation and an evaluation based on evolutionary agent-based modelling to empirically test how sustainable different strategies are for knowledge sharing in open multi-agent systems (MAS). Our results show the importance of translation-based approaches and the need for incentives to support these.
Learn more
Learning and Reasoning for Cultural Metadata Quality
This work combines semantic reasoning and machine learning to create tools that allow curators of the visual art collections to identify and correct the annotations of the artwork as well as to improve the relevance of the content-based search results in these collections. Our results show that cross-fertilization between symbolic AI and machine learning can indeed provide the tools to address the challenges of the museum curators work describing the artwork pieces and searching for the relevant images.
Learn more
> Ziming Liu
A new dense hybrid visual odometry approach
Ziming Liu, Ezio Malis, and Philippe Martinet presented a paper about hybrid visual odometry method at the IROS2022 conference, at Kyoto Japan. IROS is one of the top robotics conferences. This work is finished at the ACENTAURI team, INRIA, funded by 3IA PhD grant.
> Giovanni Neglia
Regularized Bottleneck with Early Labeling
New publication at the 34th Intl Teletraffic Congress (ITC 2022). Output of a collaboration with Nokia Bell Labs. Our approach combines elements of head network distillation, early exit classification, and bottleneck injection with the goal of reducing the average end to-end latency of AI/ML inference on constrained IoT devices.
Personalized Federated Learning through Local Memorization
New publication at the 39th Intl Conference on Machine Learning (ICML 2022). Output of a collaboration with Accenture Labs. In this work, we exploit the ability of deep neural networks to extract high quality vectorial representations (embeddings) from non-tabular data, e.g., images and text, to propose a personalization mechanism based on local memorization. Personalization is obtained by interpolating a collectively trained global model with a local k-nearest neighbors (kNN) model based on the shared representation provided by the global model.
Learn more
