OpenGVLab / OpenGVLab/Ask-Anything
How to download and process the videos for Internvid
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 3.4k
- Forks
- 268
- PR merge metrics
- No merged PRs in 30d
Description
For those data samples in VideoChat2-IT/video/conversation/videochat2/train.json, I'm wondering how these videos are downloaded and processed. I found the original Internvid(the source videos for videochat2) has different naming patterns for videos. For example, your data sample in this json file is 'LLP1dosmfIw_683.24.mp4', while the one I downloaded is '0ABL-ETtK44_00:01:55.680_00:02:00.880.mp4 '.
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 with VideoChat2-IT/video/conversation/videochat2/train.json and compare the sample filename formats described in the issue with the downloaded InternVid files. No downloader, processor, or test is named, so locate the repository entry point responsible for preparing these videos. Done means documenting the download, filename mapping, and processing steps clearly enough to reproduce the dataset.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- computer-vision, data
- Issue type
- Documentation
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100