Having built something similar with CLIP on an M1, frame sampling rate is the whole ballgame. One frame a second on 12k videos is days, keyframes only got me to an overnight run.

▲

pezgordo 2 hours ago | parent | next [-]

Maybe you need a minimal downscale version as well, I heard is very common technique in the video editing world.

Based on my experience, sampling rate can be tricky if what you are looking for lasted less than interval period.

	▲	Forgeties79 38 minutes ago \| parent [-]
		Proxies. You transcode proxies from the original media, edit off those, then you use OM for the final render. NLE’s usually let you flip between them.

▲

xnx 2 hours ago | parent | prev | next [-]

Have you tried scene detection? I would guess camera cuts are even less frequent than keyframes.

▲

mistrial9 an hour ago | parent | prev [-]

> 12k videos ?

you are pirating first-release movies for commercial purposes?

	▲	Hnrobert42 an hour ago \| parent [-]
		I think 12K is quantity not resolution.