Dimitrios Stoidis

PhD researcher at QMUL and Center for Intelligent Sensing (CIS). Privacy for speech and image data.

[C4DM at QMUL @c4dm]

We are happy to announce that we will be hosting next year's @AESorg International Conference on #AI and Machine Learning for #Audio! We are currently accepting submissions for challenges.

More information at: https://t.co/AuF8oQxk8J

[AK @_akhaliq]

Seeing the World through Your Eyes

paper page: https://t.co/KdZdy64bFx

The reflective nature of the human eye is an underappreciated source of information about what the world around us looks like. By imaging the eyes of a moving person, we can collect multiple views of a scene outside the camera's direct line of sight through the reflections in the eyes. In this paper, we reconstruct a 3D scene beyond the camera's line of sight using portrait images containing eye reflections. This task is challenging due to 1) the difficulty of accurately estimating eye poses and 2) the entangled appearance of the eye iris and the scene reflections. Our method jointly refines the cornea poses, the radiance field depicting the scene, and the observer's eye iris texture. We further propose a simple regularization prior on the iris texture pattern to improve reconstruction quality. Through various experiments on synthetic and real-world captures featuring people with varied eye colors, we demonstrate the feasibility of our approach to recover 3D scenes using eye reflections.

[Privacy Matters  @PrivacyMatters]

The Dutch Data Protection Authority has imposed a fine of €50,000 on the police for using camera cars in Rotterdam to monitor compliance with coronavirus measures without first assessing the privacy risks this might entail. https://t.co/MPe9aRGN6H

[Andrea Cavallaro @smartcameras]

.@intelsensing Winter School on #Explainable #AI (online)

An amazing lineup of speakers giving 4 tutorials & 8 talks.

Plenty of Q&A time + the opportunity to present your ideas!

Register now (free) & join us on Dec: 12-14, 19 (2-4pm GMT):

https://t.co/3dxu5l5wxX

Please RT

[Ramin @ramin_m_h]

In a new article published today in Nature MI @NatMachIntell we solved a differential equation that describes the interaction of neurons and synapses! This equation had no known closed-form solution since the year 1907!

This solution is important! 1/n

https://t.co/53qU76Ewrq

[Intelligent Sensing @intelsensing]

Generating gender-ambiguous voices for #privacy-preserving speech recognition

@Dimitri18763006 @smartcameras

#Audio #ML #SpeechRecognition #DeepLearning

Presented at #INTERSPEECH2022: https://t.co/8nHYAVBitf

Paper: https://t.co/9UnGBiI0B9

Code: https://t.co/uFTBrAMR1Q

[CORSMAL @corsmal]

Data augmentation with mixtures of max-entropy transformations for filling-level classification

@amodas_ @smartcameras @pafrossard

Presentation at #EUSIPCO2022
📆Thu Sep 1, 2-3:40 pm

📜https://t.co/IXJwP55Go5

#AI #MachineLearning #DeepLearning
@eurasip @eusipco

[CORSMAL @corsmal]

This Thursday!

Join us to learn about the project CORSMAL and audiovisual algorithms designed to understand different physical properties of containers for food and drinks manipulated by a person prior to a human-robot collaboration

Free registration: https://t.co/xIHP6lbczd

[Intelligent Sensing @intelsensing]

Training #privacy-preserving #video analytics pipelines by suppressing features that reveal information about private attributes

Chau Yi Li and Andrea Cavallaro

Presented at #ICASSP2022

#deeplearning #privacy #video #analytics #robustness #utility

https://t.co/OHgPr3SfBe

[CORSMAL @corsmal]

Next week (28-30 March): The annual CHIST-ERA Projects Seminar 2022

CORSMAL features as a CHIST-ERA #OpenScience Success Story!

Check out the programme and registration here: https://t.co/xF375gGd4C

@chistera_net @smartcameras

[Andrea Cavallaro @smartcameras]

One week to go! Register (free) to the @intelsensing online winter school on #AI #perception (1-3pm GMT on Dec, 7-10).

24 talks on multimodal sensing, computer vision and machine listening + the @corsmal challange on audiovisual classification.

https://t.co/7kdAmK2dd7

[@[email protected] at Mastodon @fborgesius]

WhatsApp: “No one outside of this chat, not even WhatsApp, can read or listen to them.”

Not true, says Propublica

https://t.co/mQCY2SDGPe

[Dimitrios Stoidis @Dimitri18763006]

Delighted to be presenting our latest paper @INTERSPEECH2021 conference today!
Feel free to check out our paper on privacy-preserving speech representations.
https://t.co/hXnCuSf7f2

[Angeliki Koutsoukou-Argyraki @AngelikiKoutso1]

An amazing discovery today during my random stroll (someplace in Greece, in a secret location)! As I took a shortcut through a tiny street, I was thrilled to see that someone had filled the place with beautifully drawn Geometry theorems! [1/9]

[PyTorch Best Practices @PyTorchPractice]

A PyTorch audio fingerprinting framework https://t.co/e5s9FB16HT #deeplearning #machinelearning #ml #ai #neuralnetworks #datascience #PyTorch

[Rachel Thomas @math_rachel]

11 Short Videos About AI Ethics

https://t.co/U8gSlUxdeG

[Yannic Kilcher 🇸🇨 @ykilcher]

🔥New Video🔥How Apple scans your phone👀In-depth analysis of iCloud's CSAM detection system, including its weak points. (Hint: it looks surprisingly easy to evade). How much privacy is preserved? Is it worth the trade-off? Watch to find out!💪
https://t.co/EybRb3IHEm
@Apple

[@ reachartwork on tumblr & bsky @reachartwork]

nightmare waluigi