metadata
license: apache-2.0
base_model: Qwen/Qwen2.5-VL-7B-Instruct
library_name: peft
pipeline_tag: video-classification
tags:
- video-classification
- advertising
ad-video-classifier
A multimodal model that classifies advertising videos by production format. The model predicts one of three classes: UGC, motion graphics, and live action.
Training and inference code is available at madup-inc/ad-video-classifier.
Usage
git clone https://github.com/madup-inc/ad-video-classifier.git
cd ad-video-classifier
pip install -r requirements.txt
huggingface-cli download MADUP/ad-video-classifier adapter_model.bin --local-dir .
python inference.py sample.mp4
License
Apache License 2.0.
Acknowledgement
This work was supported by the Ministry of Science and ICT (MSIT) and the Korea Association for ICT Promotion (KAIT) under the Advanced GPU Utilization Support Program.