| ▲ | laidoffamazon 8 hours ago | |
It’s not difficult to hack this together with CLIP. I did this with about a tenth of my movie collection last week with a GTX 1080 - though it lacks temporal understanding so you have to do the scene analysis yourself | ||
| ▲ | vhcr 4 hours ago | parent | next [-] | |
I'm guessing you're not storing the CLIP for every single frame, instead of every second or so? Also, are you using the cosine similarity? How are you finding the nearest vector? | ||
| ▲ | dynode 6 hours ago | parent | prev [-] | |
Would you be willing to share more details of what you did? | ||