Antonio Ortega

Teaching and research @uscminghsiehee, @uscviterbi, @usc, new app concepts @inqbarna, @lexttalk

[Antonio Ortega @elpenta]

@docmilanfar @theNAEng Congratulations !

[IEEE International Conference on Image Processing @ieeeICIP]

📣 #ICIP2026 invites proposals for Satellite Workshops on focused or emerging topics in image processing, vision and imaging, not specifically covered in the main conference.

📅 Submissions due 21 January 2026

🔗 Learn more: https://t.co/liaRBp9CZq

[Thomas G. Dietterich @tdietterich]

The Computer Science section of @arxiv is now requiring prior peer review for Literature Surveys and Position Papers. Details in a new blog post

[Peyman Milanfar @docmilanfar]

Michael Jordan gave a short, excellent, and provocative talk recently in Paris - here's a few key ideas

- It's all just machine learning (ML) - the AI moniker is hype

- The late Dave Rumelhart should've received a Nobel prize for his early ideas on making backprop work

1/n

[Peyman Milanfar @docmilanfar]

The tech industry in Silicon Valley runs on the considerable talents and work ethic of folks who were not born here. Many of these folks were also trained in this country in our Universities. This is our strength.

If we mess with this virtuous cycle, it is at our own peril.

[Laurent Duval (research amateur) @laurentduval]

Once-beloved topic: efficient signal, image, graph transformations like Discrete Cosine or Sine Transforms (DCT/DST), for data analysis, sparsity, compression. Antonio Ortega DCTs, DSTs and transforms on path graphs: History and recent results @elpenta

https://t.co/7DB4hXZj0y

[Karen Hao @_KarenHao]

As someone who has reported on AI for 7 years and covered China tech as well, I think the biggest lesson to be drawn from DeepSeek is the huge cracks it illustrates with the current dominant paradigm of AI development. A long thread. 1/

[Graph Signal Processing Workshop 2025 @gsp_workshop]

🚨 The 8th annual Graph Signal Processing Workshop is back this May 14-16! Held in Montreal, CA, at @Mila_Quebec, we’re covering all things graphs, signals, learning, & applications 🕸️〰️

🔗: https://t.co/s5olwuXvt7

👉🏻Abstract submission opens Feb 1

👉🏻 Registration opens Mar 20

[rafael yuste @yusterafa]

Interview (in Spanish) with @manuelansede @el_pais about NeuroTech, Neurorights and #spainneurotech. https://t.co/n6sccUTYbX via @el_pais

[Gabriel Peyré @gabrielpeyre]

The Delaunay triangulation is the dual of the Voronoi diagram. The most fundamental tool of computational geometry. https://t.co/GzE8Pi3Joz https://t.co/Y1zWHcn7Lr https://t.co/6T57pG5dOo

[Peyman Milanfar @docmilanfar]

I'm pleased to share that our recent paper with @2ptmvd has been accepted to the Philoshophical Transactions of the Royal Society. Here's the ‘Accepted Author Version’:

https://t.co/dUibTgqRF7

And here it is on arxiv without the fancy formatting:
https://t.co/0Ocmqv5sqV

1/3

[USC ECE @USCMingHsiehEE]

Congratulations to @USCViterbi researchers Urbashi Mitra, Bistra Dilkina (@BDilkina), and Gisele Ragusa! They'll provide expertise on AI/machine learning, data analytics, and algorithm design for the new @NSF Center for Pandemic Insights. https://t.co/RjgPlaMvbz

[Stanley H. Chan @stanley_h_chan]

Tutorial on Diffusion Models for Imaging and Vision

2nd edition is up on arXiv
https://t.co/fWv111nG5M

(51 pages --> 89 pages)

- Expanded VAE
- More detailed DDPM
- New section: physics of diffusion
- and more

Feedback is welcome!

[Rob Nowak @rdnowak]

We are pleased to announce plans for a special issue of Signal Processing Magazine focused on the mathematics of deep learning:

https://t.co/5lVaqNDlYP

We look forward to your submissions!

[Antonio Ortega @elpenta]

@inakib I really liked Los Detectives Salvajes, and would also recommend 2666

[Yuichi Tanaka @ychtanaka]

グラフ信号処理のためのデータセット GSP-Traffic Dataset を公開しました！　みなさんぜひ使ってみてください。
- 実際の道路ネットワーク
- SUMOによる（時変）グラフ信号
- 世界中の465都市でのシミュレーション

フィードバックもお待ちしています！
https://t.co/otLbFFAS88

[Gabriel Peyré @gabrielpeyre]

Oldies but goldies: I Daubechies, Orthonormal bases of compactly supported wavelets, 1988. Defines orthogonal wavelet bases which generalize the Haar basis. The construction is a mathematical gem that uses the Bezout theorem. https://t.co/CJPfOns350

[Antonio Ortega @elpenta]

@stanley_h_chan Congrats! Well deserved!

[Peyman Milanfar @docmilanfar]

It’s been >20 years since I published my first work on multi-frame super-res (SR) w/ Nhat Nguyen and the late great Gene Golub. Here’s my personal story of SR as I’ve experienced it from theory, to practical algorithms, to deployment in product. In a way it’s been my life’s work

[Stanley H. Chan @stanley_h_chan]

I wrote a tutorial on diffusion models for undergrad and grad students. I tried my best to give intuitive explanations for complicated equations.

Your feedback is much appreciated

Thanks to those who suggested various reading materials to me

https://t.co/fWv111nG5M