Pytorch Implementation for "Minority-Oriented Vicinity Expansion with Attentive Aggregation for Video Long-Tailed Recognition" (AAAI 2023)

Arxiv | Download Imbalanced-MiniKinetics200

1. Requirements & Environments

To run the code, you need to install requirements below. We suggest to work with torch version (1.2 ~ 1.7.1). Other versions may work fine but we haven't tested them.

pip install -r requirements.txt

2. Training & Evaluation

Please refer to subdirectories for training each VideoLT and Imbalanced-MiniKinetics200 dataset.

Cite MOVE

If you find this repository useful, please use the following entry for citation.

Contributors and Contact

If there are any questions, feel free to contact with the authors: WonJun Moon and Hyun Seok Seong.

Acknowledgement

This repository is built based on VideoLT repository.