One of the most striking things about intro computer vision explanations & courses today is how completely things have changed in the last 20 years. My “machine vision” textbook from college has near zero overlap with the subjects listed in this blog post, except for face and object recognition as goals, but the techniques taught for object and face recognition today are different from what was taught not so long ago. Seems like CNNs really flipped everything and that nobody starts off with Sobol operators or Medial Axes or Hough Transforms anymore. Most of computer graphics and computer science in general is still building on foundations from thirty, fifty, and seventy years ago, but it seems like vision has changed more dramatically than most other sub-field of CS.
at Berkeley I studied multiple papers by students of The Mighty Malik(tm); as said, they may not appear to be aging well, but the topic is far from exhausted.
Yes definitely, I had the same experience in college a couple of years ago, the AI course was about "expert systems" and that kind of old symbolic AI. No neural nets at all. But, interestingly enough I think neural nets will likely be combined with something like symbolic methods when we finally build AGI, mainly for reasoning tasks.
When I see posts like these, I immediately go to the company’s homepage to see what they’re trying to sell.
One thing that stuck out to me was the “Our technology partners” section. Is Theos actually “partnering” with companies like Google, Meta, Nvidia, OpenAI, etc, on anything? Or is Theos just using technology from these companies? If it is the latter, this seems very misleading.
Agreed. I saw MSI, and was immediately even more suspect. I imagine there’s no real depth here. There’s also typos and no real content in the post. If you’re really interested check out this post [1] which surveys a single year in computer vision. I’ve actually asked them to please do an update, but so far, they haven’t.