[GH-ISSUE #177] Has anyone run experiments on actionrecognition datasets ? #151

New issue

Open

opened 2026-10-31 21:11:45 +00:00 by bsakaguchi · 2 comments

bsakaguchi commented

2026-10-31 21:11:45 +00:00

Owner

Originally created by @Morning-YU on GitHub (Nov 10, 2021).
Original GitHub issue: https://github.com/openai/CLIP/issues/177

I saw that the experiment was done on UCF101, but according to the idea of the paper, text information needs to be provided, I don't know how to get text.

Originally created by @Morning-YU on GitHub (Nov 10, 2021). Original GitHub issue: https://github.com/openai/CLIP/issues/177 I saw that the experiment was done on UCF101, but according to the idea of the paper, text information needs to be provided, I don't know how to get text.

bsakaguchi commented

2026-10-31 21:11:46 +00:00

Author

Owner

@dragen1860 commented on GitHub (Nov 11, 2021):

simple put the ground truth label as the text.

@dragen1860 commented on GitHub (Nov 11, 2021): simple put the `ground truth label` as the text.

bsakaguchi commented

2026-10-31 21:11:46 +00:00

Author

Owner

@Rijgersberg commented on GitHub (Nov 11, 2021):

Have you seen the list of classes and templates here?
https://github.com/openai/CLIP/blob/main/data/prompts.md#ucf101

@Rijgersberg commented on GitHub (Nov 11, 2021): Have you seen the list of classes and templates here? https://github.com/openai/CLIP/blob/main/data/prompts.md#ucf101

bsakaguchi referenced this issue

2026-10-31 21:15:15 +00:00

[PR #151] [MERGED] In Compose, replace lambda function with named function #464