video-transformers mayhammad277 · COMPLETED
"⚡ Experimental implementations of Video Transformers: COOT for long-range temporal modeling, RoBERTa & VideoBERT for vision-language alignment, and CLIP for zero-shot video retrieval. Exploring SOTA attention in the video domain."
github.com/mayhammad277/video-transformers · ★ 1 · Forks 0 · Size 65 KB
SUMMARY
Technologies 6
Scored 6
Observed 6
Practices 6
Evidence 6
Skips 0
COVERAGE
Analyzed 41 files · 2 commits · 0 API calls
TECHNOLOGIES & DEPTH
Markdown LANGUAGE Depth 70
1 files · PRODUCTION
Python LANGUAGE Depth 70
31 files · PRODUCTION
NumPy LIBRARY Depth 70
22 files · PRODUCTION
Requests LIBRARY Depth 54
1 files · PRODUCTION
TypeScript LANGUAGE Depth 58
2 files · PRODUCTION
pandas LIBRARY Depth 70
9 files · PRODUCTION
PRACTICES
documentation · observedautomated_tests · absentcontinuous_integration · absentcontainerization · absentlinting · absentformatting · absent
ACTIVITY & OWNERSHIP
First commit 2026-04-10
Last commit 2026-04-10
Active months 1
Commits 2