OpenGVLab / OpenGVLab/InternVideo
Extract features from custom data.
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 2.4k
- Forks
- 160
- PR merge metrics
- No merged PRs in 30d
Description
Hello, thanks for releasing the code of this cool paper!
I would like to try the Temporal Action Localization on my own custom data. I have generated raw_frames for each video. But I struggle to understand how I extract the features from the images? How do I get the feature vector of 1280 from the VideoMAE that you extracted from the Thumos dataset for example?
Any help would be kindly appreciated!
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by tracing the temporal action localization pipeline that consumes THUMOS raw_frames and locating the VideoMAE feature-extraction entry point. Document the required preprocessing and how custom video images produce the 1280-dimensional feature vector, then validate the process on a small custom example.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- computer-vision, machine-learning
- Issue type
- Documentation
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 28/100