Associate Professor of Computer Science at @UHA68 / @Ensisa_Mulhouse machine learning - computer vision - time series - human motion analysis
Mulhouse, France
Joined September 2019
- Tweets140
- Following330
- Followers110
- Likes483
Devanne Maxime retweeted
Check out the ShapeDBA paper here: ecml-aaltd.github.io/aaltd20…
source code: github.com/MSD-IRIMAS/Weight…
Thanks to the co-authors @MaximeDevanne @stefano_berrett @jjmweber and @gforestier
Devanne Maxime retweeted
The 1st #MovementAnalysis dataset for #PhysicalRehabilitation with patients data throughout a 3w clinical care with @poppy_project will be presented at #IJCNN #WCCI #WCCI2024
🕝Thu, July 4, 2024 14:20 ML - Mixture models session
📃nguyensmai.free.fr/KeraalDat…
📽️youtu.be/3JcuXye-I4A
So excited
📣medical report & patient-therapist evaluation of the #RobotCoach #RobotPoppy for #PhysicalRehabilitation in clinical trial 🏥
by @remy_neris @CHRU_Brest @MaximeDevanne @MatSimonnet @IMTAtlantique @GenerationRobot is
👉 doi.org/10.1155/2022/5667223
youtu.be/db1XVXrc-oM
Devanne Maxime retweeted
*** Call for Papers ***
IEEE International Conference on Automatic Face and Gesture Recognition (FG 2025)
June 3 – 5, 2025, Clearwater, USA.
fg2025.ieee-biometrics.org
*** Important Dates ***
Round 1
Paper submission: September 23rd, 2024, 11:59pm
Devanne Maxime retweeted
I am again involved in organising the AALTD workshop at the ECML/PKDD conference in September in Vilnius. Papers published in Springer LNCS. Submission deadline is approaching ecml-aaltd.github.io/aaltd20…
Devanne Maxime retweeted
Last week we released aeon v0.9 which introduces the foundation of the new anomaly detection module, some fixes to pipelines, improved loading capacities for deep learning networks and deprecations to move transformations over to a new interface in 0.10. Thx to all contributiors!
Very nice week at #FG2024, ended up with our LFA Workshop discussing solutions to handle the lack of annotated face and gesture data. A big thanks to all presenters and participants! Co-organized with @DaoudiMed64, @stefano_berrett, @gforestier and @jjmweber.
We publicly released a simple code to facilitate the visualization and comparison of 1D convolution kernels learned by deep models on time series analysis tasks, mainly based on bokeh and @aeon_toolkit.
I would like to share that my paper on "Deep Learning For Time Series Classification Using New Hand-Crafted Convolution Filters" was accepted at the 2022 IEEE International Conference on Big Data done with @MaximeDevanne, @jjmweber and @gforestier.
#IEEEBigData2022
It was very useful for analyzing our models for time series classification (msd-irimas.github.io/pages/d…) and we believe it can be helpful for the community working on deep learning for time series analysis.
The code is available here: github.com/MSD-IRIMAS/filter…
It allows to generate a webpage like this one: maxime-devanne.com/pages/fil…
Devanne Maxime retweeted
bake off redux is online first, it reviews and compares recent algorithms for time series classification using the @aeon_toolkit for the vast majority of experiments link.springer.com/article/10…
Devanne Maxime retweeted
9th Workshop on Advanced Analytics and Learning on Temporal Data (AALTD 2024): ecml-aaltd.github.io/aaltd20…
Devanne Maxime retweeted
I am happy to share that my paper titled "A Supervised Variational Auto-Encoder for Human Motion Generation using Convolutional Neural Networks" has been accepted at the 4th International Conference on Pattern Recognition and Artificial Intelligence #ICPRAI2024
Devanne Maxime retweeted
9th Workshop on Advanced Analytics and Learning on Temporal Data (AALTD 2024) event located at the @ECMLPKDD 2024. Learn more about ML and temporal data analysis! @heerme @ml_labs_irl @UCDCompSci @rtavenar
👉🏼 More info: ecml-aaltd.github.io/aaltd20…
Devanne Maxime retweeted
I am glad to share that my paper titled "Finding Foundation Models for Time Series Classification with a PreText Task" has been accepted at the International Workshop on Temporal Analytics #IWTA at the Pacific-Asia Conference on Knowledge Discovery and Data Mining #PAKDD2024
Devanne Maxime retweeted
📢📢📢 Paper submissions to FG'24 main conference is over! However, you can still submit to workshops, take part in competitions, and submit a demo.
Demo submissions: fg2024.ieee-biometrics.org/c…
Workshops: fg2024.ieee-biometrics.org/w…
Competitions: fg2024.ieee-biometrics.org/c…
At #EGC2024 with @AHIsmailFawaz, @jjmweber and @gforestier to give a tutorial on Deep Learning for Time Series Classification using @aeon_toolkit. Check our dedicated DL-4-TSC webpage: msd-irimas.github.io/pages/d…
As part of the ANR DELEGATION project, we have an open Master's internship position in deep generative models for rehabilitation movements.
More information at maxime-devanne.com/jobs/inte…
#deeplearning #humanmotion #generativemodel #rehabilitation