申請取用 · Request access
This repository is publicly accessible, but you have to accept the conditions to access its files and content.
研究用 checkpoint，僅供非商業研究（CC-BY-NC-SA-4.0），逐個人工審批。
本倉庫不含任何視頻或幀。方法細節、評測結果與使用說明隨倉庫文件一併提供，審核通過後可見。
Research checkpoints for non-commercial research only (CC-BY-NC-SA-4.0), approved
manually. No video or frames are included. Method details, evaluation results and
usage instructions ship with the repository files and are visible once approved.
Log in or Sign Up to review the conditions and access this model content.
CameraJev-4B — compact camera-motion recognition
A compact camera-motion recogniser: it answers camera-movement questions — pan, tilt, truck, dolly, zoom, roll, arc, static and more — at a fraction of the size and cost of a large video-language model.
Built for throughput, so camera motion can be labelled across a whole corpus rather than sampled. Improves measurably on its base model on the standard public camera-motion benchmarks.
Quantitative results, the method, and runnable loading code are in the repository and become available once your access request is approved — this work is not yet published, so the public card is kept brief.
What you get
LoRA checkpoints over ZhuYuhan/VideoJev-4B, with their configurations. No video, frames
or training data are included.
Access
Click Request access on this page and complete the form. Requests are reviewed individually.
Licence and credit
- Licence: CC-BY-NC-SA-4.0 — non-commercial research only.
- Base model:
ZhuYuhan/VideoJev-4B(Apache-2.0), not redistributed here.
Citation
If you use this repository, please cite it. The upstream works credited above should be cited as well.
@misc{lin2026camerajev4b,
author = {Zeteng Lin and Jing Tang},
title = {CameraJev-4B: compact camera-motion recognition},
year = {2026},
howpublished = {\url{https://huggingface.co/Zeteng/CameraJev-4B}}
}
- Downloads last month
- -