DAMO-NLP-SG / DAMO-NLP-SG/VideoLLaMA2
Evaluation benchmarks (AVSSD, AVSD)
Open
- Dominant language
- Python
- Stars
- 1.3k
- Forks
- 90
- PR merge metrics
- No merged PRs in 30d
Description
Hello, thank you for this great work!
I am currently trying to reproduce the benchmark performance, but I cannot find the avssd_test.json file for AVSSD evaluation task with VGGSound and the instruction_val.json file for AVSD evaluation task.
Can you share these annotation files?
Thanks a lot in advance!
Contributor guide
No contributing guide indexed for this repository
Research direction
Start by reviewing the repository's evaluation instructions and data-release locations for the AVSSD and AVSD tasks. Confirm whether avssd_test.json and instruction_val.json are absent, then document or provide the files so both benchmark evaluations can be reproduced.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- data, machine-learning
- Issue type
- Feature
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 35/100