* update scoring/matching

* update scoring/matching

* update scoring/matching

* update scoring/matching

* update scoring/matching

* update scoring/matching

* update scoring/matching

* update scoring/matching

* update scoring/matching

* update scene_cut

* update scene_cut

* update scene_cut[A

* update scene_cut

* update scene_cut

* update scene_cut

* update scene_cut

* update scene_cut

* update scene_cut

* m

* m

* m

* m

* m

* m

* m

* m

* m

* m

* m

* m

* m

* m

* update readme

* update readme
This commit is contained in:
xyupeng 2024-04-06 16:45:59 +08:00 committed by GitHub
parent 7da8be989a
commit c4bf35727c

View file

@ -29,7 +29,7 @@ All dataset should be provided in a CSV file, which is used both for training an
- `aspect_ratio`: the aspect ratio of the video frame (height / width) (optional)
- `aes`: aesthetic score calculated by [asethetic scorer](/tools/aesthetic/README.md) (optional)
- `flow`: optical flow score calculated by [UniMatch](/tools/scoring/README.md) (optional)
- `match`: matching score of a image-text/video-text pair calculated with [clip](/tools/scoring/README.md) (optional)
- `match`: matching score of a image-text/video-text pair calculated by [CLIP](/tools/scoring/README.md) (optional)
- `cmotion`: the camera motion (optional)
Example: