Few-shotHAAD

Zenodo (CERN European Organization for Nuclear Research) 2026 Open access

Read full text
Authors: Koichiro Kamide, Shunsuke Sakai, Shun Maeda, Chunzhi Gu, Chao Zhang
DOI: 10.5281/zenodo.18147989
Cited by: 0

Abstract

This is the official release of the code for reproducing the experiments in: "Few-shot human action anomaly detection via a unified contrastive learning framework" (Knowledge-Based Systems). Reproducibility Environment: Python 3.8, PyTorch 1.7.1 Setup: bash prepare/create_env.sh Dataset: HumanAct12 (see README for download/instructions) Checkpoints: bash prepare/download_checkpoint.sh Scripts Training: bash run_train.sh Evaluation: bash run_test.sh See README for full instructions.

Publication details

Journal / source
Zenodo (CERN European Organization for Nuclear Research)
Publication date
4 January 2026