Semi-Supervised Classification With Pairwise Constraints: A Case Study on Animal Re-identification from Video

1. Data

The data is from repository: Animal Re-Identification from Video.

2. Code for semi-supervised learning (Python)

The notebooks are stored in python folder. It needs the features files (RGB, HOG, LBP, AE and MN2) for the five videos splitted in the both parts.

3. Code for the constrained clustering (MATLAB)

The code is in folder MATLAB. It needs the data files for the five videos (bounding boxes and constraints). They are named as in the data repository Animal Re-Identification from Video and stored in folder “features/features”.

4. Citing

@article{kuncheva2024semi-supervised,
  title = {Semi-supervised classification with pairwise constraints: A case study on animal identification from video},
  journal = {Information Fusion},
  volume = {104},
  pages = {102188},
  year = {2024},
  issn = {1566-2535},
  doi = {10.1016/j.inffus.2023.102188},
  author = {Ludmila I. Kuncheva and José Luis Garrido-Labrador and Ismael Ramos-Pérez and Samuel L. Hennessey and Juan J. Rodríguez},
}