Video Watermarking: Safeguarding Your Video from (Unauthorized) Annotations by Video-based LLMs [ICML Workshop 2024 🔥]

Paper Jinmin Li*, Kuofeng Gao*, Yang Bai, Jingyun Zhang, Shu-Tao Xia

* Equally contributing first authors

Installation 🔧

Following VideoChatGPT: we recommend setting up a conda environment for the project:

conda create --name=video_chatgpt python=3.10
conda activate video_chatgpt

git clone https://github.com/mbzuai-oryx/Video-ChatGPT.git
cd Video-ChatGPT
pip install -r requirements.txt

export PYTHONPATH="./:$PYTHONPATH"

Additionally, install FlashAttention for training,

pip install ninja

git clone https://github.com/HazyResearch/flash-attention.git
cd flash-attention
git checkout v1.0.7
python setup.py install

---

Training 🚋

for videochatgpt:

• bash run_slen_flow_videochatgpt_100.sh
• bash run_videochatgpt_100.sh

for videochat:

• bash run_slen_flow_videochat_100.sh
• bash run_videochat_100.sh

---

Evaluation 📊

• bash run_eval_caption.sh
• bash run_eval_clip_text.sh
• run_eval_gpt4_slen_100.sh
• run_eval_gpt_slen_100.sh

---

Dataset:

To do

Acknowledgements 🙏

• VideoChatGPT

License 📜

This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.