Frame-level bit-allocation of DMC model from ACM MM2022
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 829
- Forks
- 138
- Avg merge
- 1d 2h
- Merged PRs (30d)
- 1
Description
Hello, thank you for the work and sharing your code.
We have a question after running the program following the provided test instruction. We drawing the per-frame PSNR value recorded in the output json file (as shown in the figure below), we found that there seems to be a frame-level bit allocation mechanism in the DMC model. However, we could not find any information on frame-level bit allocation in the proposed paper or in the released code.
Can you provide some details on how your implementation does the bit allocation between each frame or any insight into such phenomenon?
Contributor guide
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 following the provided test instruction and inspecting the per-frame PSNR values in the output JSON for Jockey. Compare those observations with the released code and the ACM MM2022 paper. Done means documenting how the DMC implementation allocates bits between frames or explaining the observed phenomenon.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Documentation
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100