Validate whether yolo bbox pseudolabels are consistent across time.

swiss-ai / ml-4m

4M: Massively Multimodal Masked Modeling (NeurIPS 2023 Spotlight)

Apache License 2.0

0 stars 0 forks source link

Validate whether yolo bbox pseudolabels are consistent across time. #6

Open kdu4108 opened 3 months ago

kdu4108 commented 3 months ago

How consistent are pseudolabels for consecutive frames of a video? Take a couple random videos and spot-check the yolo outputs and identify whether it feels consistent.

definition of done: write up your vibe check along with some example images here.

kdu4108 commented 3 months ago

Look at all the frames from 3 videos from both HDVILA and HowTo100M (at 5FPS), make sure they look okay or identify frames that look off. Include some example frames here :) @yahya010

markus583 commented 2 months ago

push @yahya010