PadCaptioner-3B

PadCaptioner-3B

Official checkpoint of PadCaptioner (ECCV 2026): Parallelized Autoregressive Decoding for Omni-Modal Dense Video Captioning.

• Paper: https://arxiv.org/abs/2607.02963
• Code: https://github.com/showlab/PadCaptioner
• Data: https://huggingface.co/datasets/wenzhengzeng/PadCaptioner-Data

See the GitHub repo for installation, inference and evaluation instructions.

Citation

If you find our work useful, please consider citing:

@inproceedings{zeng2026parallelized,
  title={Parallelized Autoregressive Decoding for Omni-Modal Dense Video Captioning},
  author={Zeng, Wenzheng and Jiao, Siyi and Gao, Chen and Ng, Hwee Tou and Shou, Mike Zheng},
  booktitle={European Conference on Computer Vision},
  pages={189--209},
  year={2026},
  organization={Springer}
}