openai/CLIP
1
0
Fork 0
mirror of https://github.com/openai/CLIP.git synced 2026-11-05 01:37:26 +00:00
Code Issues 274 Projects Packages Wiki Activity

[GH-ISSUE #28] Can CLIP apply to video? #25

New issue
Closed
opened 2026-10-31 21:10:01 +00:00 by bsakaguchi · 5 comments
bsakaguchi commented 2026-10-31 21:10:01 +00:00
Owner
Copy link

Originally created by @haofanwang on GitHub (Jan 28, 2021).
Original GitHub issue: https://github.com/openai/CLIP/issues/28

As many details about how you collect the datasets are missed, I would like to know whether it is possible to apply the pretrained CLIP on text-image pairs to retrieve videos (given a text)?

Originally created by @haofanwang on GitHub (Jan 28, 2021). Original GitHub issue: https://github.com/openai/CLIP/issues/28 As many details about how you collect the datasets are missed, I would like to know whether it is possible to apply the pretrained CLIP on text-image pairs to retrieve videos (given a text)?
bsakaguchi commented 2026-10-31 21:10:02 +00:00
Author
Owner
Copy link

@jongwook commented on GitHub (Jan 29, 2021):

In the eval suite, we used the middle frame of each clip as a lower bound of the performance. At the cost of additional compute, you can also use more (or all) frames and take the average of their features to get a more robust representation of the video clip.

<!-- gh-comment-id:769480568 --> @jongwook commented on GitHub (Jan 29, 2021): In the eval suite, we used the middle frame of each clip as a lower bound of the performance. At the cost of additional compute, you can also use more (or all) frames and take the average of their features to get a more robust representation of the video clip.
bsakaguchi commented 2026-10-31 21:10:02 +00:00
Author
Owner
Copy link

@dmoham1476 commented on GitHub (Jan 30, 2021):

Yes tried CLIP with live streaming!

<!-- gh-comment-id:770118299 --> @dmoham1476 commented on GitHub (Jan 30, 2021): Yes tried CLIP with live streaming!
bsakaguchi commented 2026-10-31 21:10:02 +00:00
Author
Owner
Copy link

@AmeerHamza111 commented on GitHub (Jan 30, 2021):

Can you please share some information on how to train it on live stream or video for that matter. Please

<!-- gh-comment-id:770162420 --> @AmeerHamza111 commented on GitHub (Jan 30, 2021): Can you please share some information on how to train it on live stream or video for that matter. Please
bsakaguchi commented 2026-10-31 21:10:02 +00:00
Author
Owner
Copy link

@Newmu commented on GitHub (Jan 31, 2021):

Additionally, Appendix E.3 in the paper describes our experiments on video recognition for some more details.

<!-- gh-comment-id:770317530 --> @Newmu commented on GitHub (Jan 31, 2021): Additionally, Appendix E.3 in the paper describes our experiments on video recognition for some more details.
bsakaguchi commented 2026-10-31 21:10:02 +00:00
Author
Owner
Copy link

@Tortoise17 commented on GitHub (Oct 7, 2021):

@Newmu awesome. Can you just share the command line for the video live and recorded usage with clip. it would be kind help.

<!-- gh-comment-id:937625124 --> @Tortoise17 commented on GitHub (Oct 7, 2021): @Newmu awesome. Can you just share the command line for the video live and recorded usage with clip. it would be kind help.
Sign in to join this conversation.
No Branch/Tag specified
Branches Tags
main
codex/pin-github-workflow-refs-20260325-132838
jongwook/issue-396
jongwook-patch-1
No results found.
Labels
Clear labels   
pull-request
Mirrored from GitHub Pull Request

No labels
pull-request
Milestone
Clear milestone
No items
No milestone
Projects
Clear projects
No items
No project
Assignees
Clear assignees
No assignees
1 participant
Notifications
Due date
The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Dependencies

No dependencies set.

Reference
openai/CLIP#25
No description provided.