IG

[IG @ioangatop]

I am super excited to share “Self-Supervised VAEs” (https://t.co/2unkA05euW) with @jmtomczak! selfVAEs utilize deterministic and discrete variational posteriors, allows to train deep hierarchical models efficiently, by breaking down complex distributions into simpler ones. (1/6)

[IG @ioangatop]

@glbaumann legendary workflow https://t.co/IFRH3YUXyO

[IG @ioangatop]

@jmtomczak @a_kzna let’s go 👏

[Inferam @InferamAI]

Whoever invented the sewing machine was a genius.
https://t.co/DqtsFoVEiT

[IG @ioangatop]

@ducha_aiki @tommiekerssies @dcdegeus Awesome paper, thanks for sharing the code as well!

[Raspberry Pi Foundation @RaspberryPi_org]

10K FOLLOWER GIVEAWAY 🎉🎈🎁

To celebrate 10K followers on Twitter, we're giving away 3x Raspberry Pi Foundation tote bags containing Raspberry Pi branded goodies 😍 Winners will be randomly selected on Friday, 19 May 2023.

To enter: Follow us, like & RT this tweet.

Good luck!

[IG @ioangatop]

@alfcnz Note the “j” at the end indicates an imaginary unit

[Niels Rogge @NielsRogge]

OWL-ViT by @GoogleAI is now available @huggingface Transformers. The model is a minimal extension of CLIP for zero-shot object detection given text queries. 🤯

🥳 It has impressive generalization capabilities and is a great first step for open-vocabulary object detection!
(1/2)

[Auke Wiggers @aukejw]

The MobileCodec paper is now online: https://t.co/9E27v5Vrtd

Check it out if you want to know how we were able to deploy a neural video codec to a mobile phone and decode 720p video in real time 📲

[Dr. Tech @doctechmd]

Fixing bugs in your code

[IG @ioangatop]

@aukejw @yinhaozhu @TacoCohen Congrats Auke, great podcast!

[IG @ioangatop]

@jmtomczak @SpringerNature Awesome work Jakub!

[IG @ioangatop]

A great book dedicated to deep generative models, along with code to dive deep; Awesome work Jakub!

[Jakub Tomczak @jmtomczak]

I am excited to announce that my book, "Deep Generative Modeling", is available online and in print (@SpringerNature): https://t.co/PkeTCJ0IuN
Code used in the book is freely available online: https://t.co/A7Peb2aERB (1/4)

[martin goodson @martingoodson]

@giffmana A point made very well by @alexeyab84 at his talk last night at the London Machine Learning Meetup.

[Keenan Crane @keenanisalive]

A powerful idea in math (that nobody teaches you directly…):

If you don't know how to map between two "things," you can often map each of them to the same "canonical thing."

Then you can just go from the 1st thing to the canonical thing, and back to the 2nd thing. [1/n]

[Kosta Derpanis @CSProfKGD]

Another example of mapping between two "things" utilizing a "canonical thing".

Homography between two camera views induced by a 3D plane.

From my intro to #ComputerVision course: https://t.co/Cm7cuYh3hB

[Amsterdam Data Science @ams_ds]

We are very happy to announce the winners of the @ams_ds Thesis Awards 2021! Congratulations to BSc #Thesis #Award winner Martine Toering! Well done on your interesting research project: “Self-supervised Video Representation Learning with Cross-Stream Prototypical Contrasting”.

[UvA_DSC @uva_dsc]

Congrats to @MartineToering for winning an @ams_ds award for her MsC thesis. Collab with @BrainCreators . @UvA_Amsterdam graduate! (cc @cgmsnoek) The @uva_dsc is happy to support these awards.

[IG @ioangatop]

Congrats @MartineToering! Honoured to be part of this!

[Cees Snoek @cgmsnoek]

📢@UvA_Amsterdam #Master #AI student scores @ams_ds thesis #award, congrats @MartineToering (and proud supervisor @vtaohu) 🥳https://t.co/NqP5Md9NEw

[Cees Snoek @cgmsnoek]

📢@UvA_Amsterdam #Master #AI student scores @ams_ds thesis #award, congrats @MartineToering (and proud supervisor @vtaohu) 🥳https://t.co/NqP5Md9NEw

[IG @ioangatop]

@aukejw Looks great! 👏👏