QuerYD: A video dataset with high-quality textual and audio narrations deepai.org/publication/qu… by Andreea-Maria Oncescu et al. #ComputerVision #PatternRecognition

Generating Beautiful #NeuralNetwork Visualizations - KDnuggets buff.ly/3hteIwG

Ça semble mission impossible de rivaliser avec les superbes patisseries d'Élodie Condemi 🍰 mais si vous voulez m'aider à ne pas avoir l'air trop ridicule, vous pouvez voter pour moi pour le titre d'Alsacien(ne) de la semaine😁 Journal L'Alsace 👇 lalsace.fr/societe/2021/0…

✔️ Portes ouvertes en live pour l'IUT de Saint-Dié ! 👉 Rendez-vous le 13 février formations B.U.T. / Licences professionnelles #butgeii #butinfo #butmmi #lpsarii #lpamio #lpmn #lptourisme #formations #iutsdjpo21 iutsd.univ-lorraine.fr/?p=10539 Lorraine

Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion deepai.org/publication/mo… by Ho Kei Cheng et al. #ComputerVision #PatternRecognition

Noise-Aware Saliency Prediction for Videos with Incomplete Gaze Data deepai.org/publication/no… by Ekta Prashnani et al. including Orazio Gallo #LossFunction #DeepLearning

VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text deepai.org/publication/va… by Hassan Akbari et al. including yin cui #ComputerScience #Learning

🎞️ VALUE: A video-and-language understanding evaluation benchmark to test models that are generalizable to diverse tasks and domains. It's an assemblage of 11 datasets over 3 tasks: text-to-video retrieval, video question answering; and video captioning. paperswithcode.com/dataset/value

🤖 BEHAVIOR: A new benchmark with the 100 household activities that represent a new challenge for embodied AI solutions. Agents need to navigate and manipulate the simulated environment with the goal of accomplishing the activities. paperswithcode.com/dataset/behavi…

Présentation de Mounir Bendali-Braham ! #orasis2021

Talk de Jean Feydy, prix de thèse 2020 de l’AFRIF, introduit par Jonathan Weber #orasis2021

Today i present my paper at IEEE International Conference on Image Processing link : ieeexplore.ieee.org/document/95061…

Interested in Deep Learning and human motion analysis ? Apply to our Master internship position in deep generative models for skeleton-based human motion. More information at maxime-devanne.com/jobs/internshi… #deeplearning #humanmotion #generativemodel #timeseries

Unidentified Video Objects (UVO): a new benchmark for open-world object segmentation in videos. UVO aims to enable development and research of machine learning methods for more comprehensive video understanding. paperswithcode.com/dataset/uvo

Soutenance de Mounir Bendali-Braham sur la classification de vidéos de foule. Un doctorant de plus qui va quitter le nid 😉

We have an open research engineer position on virtual reality for rehabilitation movements assessment. The position is in the MSD research group of IRIMAS Institute at UHA, in collaboration with @GEscrivaBoulley from LISEC Lab. #virtualreality #humanmotion #rehabilitation

THREAD : Les 10 sites gratuits qui vont révolutionner votre vie de dev. Voici ma liste ultime des outils en ligne qui m'ont économisé des journées entières de boulot ⤵️

Call for papers: Workshop On Learning With Few or Without Annotated Face, Body and Gesture Data at #FG2023 IEEE Biometrics Submission deadline extended to 09/22/2022 More info: sites.google.com/view/lfa-fg202… Co-organized with Daoudi Mohamed, Stefano Berretti, Germain Forestier and Jonathan Weber

We (Charlotte Pelletier Sylvain Lobry Germain Forestier and Camille Kurtz) are organizing a special session at JURSE 2023 about "Deep learning approaches for multi-temporal and multi-modal data processing and analysis for urban areas". charlotte-pel.github.io/jurse2023_dl/