kagu-torch 0.0.1

Official implementation of Towards Automated Ethogramming: Cognitively-Inspired Event Segmentation for Streaming Wildlife Video Monitoring

kagu-torch

Official implementation for IJCV paper Towards Automated Ethogramming: Cognitively-Inspired Event Segmentation for Wildlife Monitoring

---

Overview

Documentation

Checkout the documentation of code to learn more details.

Installation

pip install kagu-torch # with pip from PyPI
pip install git+'https://github.com/ramyamounir/kagu-torch' # with GitHub

Training

Use the provided python training script to train or multiple gpus. Bash scripts with CLI arguments are provided in the helper_scripts

We use the DDPW library to enable scaling up our training to SLURM with one line of code.

---

Citing our paper

If you find our approaches useful in your research, please consider citing:

@article{mounir2023towards,
  title={Towards Automated Ethogramming: Cognitively-Inspired Event Segmentation for Streaming Wildlife Video Monitoring},
  author={Mounir, Ramy and Shahabaz, Ahmed and Gula, Roman and Theuerkauf, J{\"o}rn and Sarkar, Sudeep},
  journal={International Journal of Computer Vision},
  pages={1--31},
  year={2023},
  publisher={Springer}
}