LAION-AI / LAION-AI/temporal-embedding-aggregation
Architecture Tuning: Try out other poolers
Open
Nobody has claimed this yet.
research
- Dominant language
- Python
- Stars
- 32
- Forks
- 4
- PR merge metrics
- No merged PRs in 30d
Description
- cross attention
- merge in temporal dimension within the CLIP model
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 reviewing the existing temporal embedding aggregation flow and its CLIP integration. The issue mentions trying other poolers, cross attention, and merging in the temporal dimension, but names no files or tests. Done would require a decided architecture and an evaluation showing the selected approach works.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100