Kymatio retweeted
D-day for Edouard Oyallon who is defending his HDR entitled "Contributions to Local, Asynchronous and Decentralized Learning, and to Geometric Deep Learning"
Kymatio retweeted
The Music Cognition Group is excited to welcome Dr. @lostanlen for a captivating talk on music signal processing next week @UvA_Amsterdam. Really glad our connection from Timbre 2023 has evolved into collaboration! Check out the poster for more details! #musicscience
Kymatio retweeted
#ISMIR2023 final credits
Gotta hand it to @cyrusasfa and @frozenmango for turning ten years of research on time–frequency scattering into a series of Colab notebooks that anyone can use.
Thanks to all the attendees. I was very pleased with the turnout, up until 6pm!
Kymatio retweeted
If you're attending ISMIR and curious about wavelet transforms applied to audio, come check out our tutorial on Sunday afternoon! 🌊🌊🌊
You’re unable to view this Post because this account owner limits who can view their Posts. Learn more
Kymatio retweeted
"Mesostructures: Beyond Spectrogram Loss in Differentiable Time–Frequency Analysis" is out!
with @cyrusasfa, Han Han, @Tsingmoon, Mathieu Lagrange, and Gÿorgy Fazekas
made with @KymatioWavelets
The JAES special issue has been published! I'm honored by working with great DAFx researchers as a guest editor.
Special Issue on New Trends in Audio Effects II
aes.org/journal/online/JAES_…
Kymatio retweeted
PhD for hire!
"Theory and implementation of multi-resolution neural networks"
with applications to #audio #AI
at @LaboLS2N (Nantes🦀)
in partnership with @ari_oeaw (Vienna 🎻)
duration: 3 years
funding: @AgenceRecherche
start date: negotiable
audio.ls2n.fr/2023/07/11/phd…
Kymatio retweeted
I am looking for a PhD student in MIR! 🎓
to work on self-supervised learning in multitrack music
You will be employed by @Deezer Research
co-advised by R. Hennequin + me
based in Paris 🪗 and visiting my lab in Nantes 🦀
Start: Dec. 2022☃️ or later
deezerjobs.com/fr/postes/pos…
Kymatio retweeted
I'm excited to share a paper on parametric scattering networks, accepted as an oral spotlight to #CVPR2022!
Work led by Shanel Gauthier & @benjamintherien w/ Laurent @ScatteringSepoy @irinarish @ebelilov @meickenberg & the @mrguywolf
Paper @CVPR 👉🏾 openaccess.thecvf.com/conten…
1/N
Kymatio retweeted
Laura Cros Vila (KTH) presents musical instrument recognition with 1D scattering
#Kymatio22
Kymatio retweeted
Welcome to Nantes, @ScatteringSepoy!
Here's him with @rastegah writing @KymatioWavelets code in preparation for #Kymatio22
Behind us is the Castle of the Dukes of Brittany
Kymatio retweeted
"We are #Kymatio22"
A word cloud made from the research interests of our workshop participants
kymatio.cargo.site
Kymatio retweeted
Wonderful work by Kaitlin Stouffer who characterized the 3D spatial distribution of #tau tangles in #Alzheimer’s disease using multi-modal image registration with a scattering transform. #AAIC2021
Kymatio retweeted
[2103.09247] Sihao Cheng, Brice Ménard: Weak lensing scattering transform: dark energy and neutrino mass sensitivity arxiv.org/abs/2103.09247 arxiv.org/pdf/2103.09247.pdf #astro_ph_CO
Kymatio retweeted
Here's the publications list from that group:
di.ens.fr/data/publications/
Mallat has some wonderful videos on deep scattering networks easily found on YouTube. I was surprised at what a good lecturer he is, and really made some of the concepts much more clear to me as I watched...
Kymatio retweeted
Oldies but goldies: Taubman, High performance scalable image compression with EBCOT, 2000. JPEG2k performs an arithmetic coding of Wavelets coefficients of the image. Coefficients are quantized and coded bit by bit to provide a progressive coding. en.wikipedia.org/wiki/JPEG_2…
Kymatio retweeted
Very proud to share the debut first-author paper by Bruno Regaldo, whom I supervise towards PhD. We are extending the Wavelet Scattering Transform, a statistical analysis tool for complex structures, to polarization maps :
arxiv.org/abs/2007.08242
Kymatio retweeted
Kymatio – Python library for wavelet scattering transforms in 1-D, 2-D, and 3-D. Differentiable, GPU-accelerated, and backend-agnostic
kymat.io/
ArXiv
arxiv.org/abs/1812.11214






























