Skip to content

Issues: swiss-ai/ml-4m

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

13 Open 3 Closed
13 Open 3 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

Add train/val/test split script for raw
#20 opened Jul 23, 2024 by kdu4108
@markus583
1
Transform from video_description modality to video_global_description modality. nice to have
#18 opened Jul 19, 2024 by kdu4108
@markus583
Transform from v2d format into a metadata format and save in metadata/ directory. under review
#16 opened Jul 16, 2024 by kdu4108
@markus583
4
Transform from v2d format into video_description format and save in video_description/ directory. in progress
#13 opened Jul 4, 2024 by kdu4108
@markus583 @smontariol
Transform from v2d format into video_transcript format and save in video_transcript/ directory. in progress under review
#12 opened Jul 4, 2024 by kdu4108
@markus583
Transform from video_rgb format into video_det format and save in video_det/ directory. in progress under review
#11 opened Jul 4, 2024 by kdu4108
@yahya010
Transform from v2d format into video_rgb format and save in video_rgb/ directory in progress under review
#10 opened Jul 4, 2024 by kdu4108
@kdu4108 @yahya010
2
Transform from video_rgb format into video_tok_rgb format and save in video_tok_rgb/ directory. in progress under review
#9 opened Jul 4, 2024 by kdu4108
@markus583
3
Validate whether yolo bbox pseudolabels are consistent across time.
#6 opened Jul 3, 2024 by kdu4108
@yahya010
2
Implement a masking strategy which masks consistently across temporal frames.
#5 opened Jun 21, 2024 by kdu4108
Implement the encoder embeddings to encode which frame it is (a temporal embedding, in addition to the patch position and modality embeddings).
#4 opened Jun 21, 2024 by kdu4108
1
[PARENT ISSUE] Data preprocessing and pseudolabeling in progress
#3 opened Jun 21, 2024 by kdu4108
@kdu4108 @markus583 @yahya010
7
[PARENT ISSUE] Implement the temporal changes in 4M to account for video
#2 opened Jun 21, 2024 by kdu4108
@kdu4108 @garjania
2
ProTip! Find all open issues with in progress development work with linked:pr.