Unverified50% confidenceBenchmarkExact time
The CapMem benchmark dataset contains 75 videos with a total duration of 33.7 hours, 1,000 manually annotated multiple-choice questions, covering 16 different scenarios.
1
Sources
50%
Confidence
Long-term
Relevance
9/17/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedThe GPU computing resources consumed to generate a single 10-second high-quality AI video may be tens of times greater than those required to generate a single image.69% similarUnverifiedStop-motion animation is played back at 24 frames per second, and a 90-minute film requires the capture of more than 120,000 frames.67% similarUnverifiedThe Dancing Stick Figures dataset contains 1,430 six-second short video clips, totaling 514,800 annotated frames.66% similarUnverified视频生成任务的显存占用约为同分辨率图像任务的10–30倍66% similarUnverifiedMeta's Ego4D project collected over 3,670 hours of first-person perspective daily activity video.66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/928364API
curl https://kongchang.com/api/v1/knowledge/claims/928364MCP
get_claim(id=928364)