Searching...
10 results for “computer vision”
Concept5 mentions across episodes
Vision
...computer vision, which was the office dataset that was released from, from our lab actually, back in 2010.
4:49:47 / 4:51:23
from transcript4:49:47 – 4:51:23
...computer vision, at least until recently, is a pet peeve of mine. People always say like, oh, computer vision models are not robust. It will recognize a cow, but you put it on the beach, it will fail completely. Not at all. But this has been solved f
5:08:57 / 5:10:00
from transcript5:08:57 – 5:10:00
...computer vision as a field, we have been doing bits and pieces. For example, one important revolution that has happened in three d computer vision was a Neural Radiance Field or NeRF, and that was done by our cofounder Ben Mildenhall and and his coll
19:28 / 20:32
from transcript19:28 – 20:32
...in computer vision for 2024, and they blew us away with the complete overview. As a special bonus, we also got a bonus talk from Vik Korapati at Moondream, who gave an incredible talk at this year's AI Engineer World's Fair on his tiny 500,000,000 pa
1:32 / 2:36
from transcript1:32 – 2:36
...Edge learning is the other end of the spectrum, and it's probably more financially tangible for the investor community right now. These products, they come preprogrammed for specific applications, but then they're trained with just as few as five to
16:30 / 17:34
from transcript16:30 – 17:34
...rules based vision is great for a lot of things, but not for things very subtle or nuanced tasks with a great deal of variation. Those sorts of tasks, you'd still usually have a human performing them because, frankly, it's just hard to quantify them
17:59 / 19:37
from transcript17:59 – 19:37
Those sorts of tasks, you'd still usually have a human performing them because, frankly, it's just hard to quantify them to then program them. Maybe an example of that would be inspecting a phone case for very subtle defects. There's obviously a wide
15:41 / 16:49
from transcript15:41 – 16:49
...for machine vision. Edge learning is the other end of the spectrum, and it's probably more financially tangible for the investor community right now. These products, they come preprogrammed for specific applications, but then they're trained with jus
18:39 / 20:48
from transcript18:39 – 20:48
...as a computer vision scientist for me to experiment what the world is.
17:58 / 19:06
from transcript17:58 – 19:06
Have a podcast?
Run your podcast through Clypt
Get ranked clips, hooks, and ready-to-post copy from your own episodes. Free to try.