Computer Vision Study Group Session on BLIP-2

In this session of Computer Vision Study Group, Johannes walks us through the paper BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models.

[@studyingAI]

I like your story! Thank you so much to sharing it!

[@juancamachomohedano6118]

Great intro with the story! Nice and easy presentation. Thank you!

[@johanneskolbe6891]

Thank you :)

[@kemalariboga]

Thank you for your efforts! It's a great video. Also, the stories at the beginning are always my favorite, lol.

[@johanneskolbe6891]

Thank you, I have to admit the stories are also what I have most fun with when creating the presentations ;)

[@wei-lunchiu2366]

best BLIP2 explanation on the youtube!

[@objectijustmusic1476]

Good explaination! Answered some of the questions I had while reading the paper

[@nacelle_strike]

18:51에 나오는 그림은 query가 text token과 연결되면 안될것이다.

[@ruiqiu4423]

I think you are right, query token cannot attend text token.

[@gangavaramkrishnappanagate2204]

very good explanation , Thank you

[@mrtago8973]

Awesome video and great explanation! Keep it up!

[@josephtsangko3558]

Great job!

[@IntuitiveAndExhaustive]

I enjoyed your story!

[@bilalbayrakdar7100]

not the most technical group session but thanks for your effort.

[@pranav_tushar_sg]

Thanks!

[@thiagarajamuralidaran1371]

Thanks

[@IsidroTulis-o8r]

Skiles Circle

[@KittyRuby-t8u]

Shanahan River

[@kafkatamurra]

czcams.com/video/k0DAtZCCl1w/video.html Based on the paper in this step, query tokens only attend to each other, whereas text tokens attend to all query tokens and the previous text tokens.

[@RabiaKarakuş-k5w]

Alanna Crescent

[@ScotDemus-s6u]

Jasper Fork

[@JeriMetivier-s3b]

Keeling Mountain

[@BoyleFitch-f7h]

Orville Court

[@MarcyFowler-q3u]

Austen Centers

[@SharonWilliams-z9k]

Hettinger Ramp

[@PaulHayes-d5v]

Eliza Cliff