Görkem Polat

AI practicioner

[Görkem Polat @gorkemP]

@umutcan_duman Check this out then https://t.co/u2Vr4Ny45Z

[David Pantera @davidpantera_]

Two of us filmed this on a couple phones, and we used Atlas to turn it into a short film. This is just a clip from the @theworldlabs tech blog

Atlas is able to generate the parts of the scene that none of the cameras actually filmed.

It can freeze time, allowing you to reframe shots to positions never filmed, then resume.

View events from impossible angles because Atlas knows what was there.

[Görkem Polat @gorkemP]

@__paleologo I have been using a custom GPT for myself for the same reason, but this really raises the bar very high.

[Görkem Polat @gorkemP]

@kkaank Ortalama hizdan mi?

[@sharib @vision_sharib]

PhD studentship is available in my group. Please apply if you are interested. At this time it is only open for the UK students.

I am looking for a motivated #PhD student with background in #computervision and #computergraphics with good coding skills.

https://t.co/bdEX0mXC0q

[Görkem Polat @gorkemP]

@FeTS_Challenge Is the public recording of this workshop available anywhere?

[Görkem Polat @gorkemP]

@NoContextBrits This is not true, please stop posting this occasionally.

[Görkem Polat @gorkemP]

@ML_Spring What do 'output layer learning rate' and 'input layer learning rate' mean here?

[EndoCV @cv_endo]

Thanks to all the participants and collaborators - our paper on assessing the generalisability of #deeplearning  methods for #polyp segmentation and detection tasks led by @vision_sharib - a #multicentre study is now published at @SciReports

Full article: https://t.co/Gi1NhHce6J

[@sharib @vision_sharib]

Join @DemiWorkshop #MICCAI2023 - our initiative towards tackling dataset challenges in medical imaging - learn more from our excellent keynotes @james_y_zou and @QiDou_
When: October 8th
Where: Room 3, Level 1, at the Vancouver Convention Centre (online available)

[Görkem Polat @gorkemP]

@SeckinCanSahin benim threshold da 5 dk :)

[Encord @encord_team]

🤺 Mask-RCNN vs. Per-SAM

We put two object segmentation models to the test to see how well they handle few-shot learning.

🔗 Read our blog for the results: https://t.co/YvwvUOxAOC

[METU / ODTÜ @METU_ODTU]

Öğrencisi olduğun andan itibaren kendini evinde hissedeceğin bir üniversitede okumak istiyorsan, sen de ODTÜ’lü olmalısın hocam. 🏡 Biz sadece bir üniversite değil, büyük bir aileyiz. ❤️🤍

#yks2023 #yks #ODTÜ #METU #ortadoğutekniküniversitesi #middleeasttechnicaluniversity

[Görkem Polat @gorkemP]

@onatm Burnuma LLM kokulari geliyor :)

[Görkem Polat @gorkemP]

@buyukozcu Andrej karpathy bolumu de fena degil, tesla ve computer vision ustune konusuyorlar genelde

[Encord @encord_team]

Successful summer offsite last week filled with strategic planning 🤫, laughter yoga 🧘‍♀️ & perfect weather for rooftop drinks ☀

[Encord @encord_team]

🆕 Introducing the Search Anything Model

Search Anything is a unified framework that combines natural language, visual property, similarity, and metadata search.

https://t.co/dktp1t2jFm

[Görkem Polat @gorkemP]

@fcakyon @obsstech Big cograts!

[Görkem Polat @gorkemP]

@AngryTomtweets @fcakyon @eceisikpolat

[Görkem Polat @gorkemP]

@erogol Same also applies for faiss <> torch

[Görkem Polat @gorkemP]

@hoijnet Encord Active https://t.co/2Bf2UTbt6m