Suspicious Activity Recognition Dataset

This dataset is prepared by acquiring two existing datasets after getting permissions from the authors of those datasets. The existing datasets where the subsets are taken for this dataset are:HMDB 51 Dataset: https://serre.lab.brown.edu/hmdb51.html and https://www.kaggle.com/datasets/easonlll/hmdb51 AIDER Dataset: https://zenodo.org/records/3888300#.XvCPQUUzaUkCite: Please cite the following paper for this dataset:Saba, Tanzila, Amjad Rehman, Rabia Latif, Suliman Mohamed Fati, Mudassar Raza, and Muhammad Sharif. "Suspicious activity recognition using proposed deep L4-branched-ActionNet with entropy coded ant colony system optimization." <i>IEEE Access</i> 9 (2021): 89181-89197.<br>

本数据集通过获得两份现有数据集的作者授权，获取其对应数据后构建完成。本数据集所采用的子集来源如下：
1. HMDB 51数据集（HMDB 51 Dataset）：https://serre.lab.brown.edu/hmdb51.html 与 https://www.kaggle.com/datasets/easonlll/hmdb51
2. AIDER数据集（AIDER Dataset）：https://zenodo.org/records/3888300#.XvCPQUUzaUk

引用说明：若使用本数据集，请引用以下论文：
Saba, Tanzila、Amjad Rehman、Rabia Latif、Suliman Mohamed Fati、Mudassar Raza 及 Muhammad Sharif. “基于所提出的深度L4分支ActionNet与熵编码蚁群系统优化的异常行为识别”，*IEEE 接入*（IEEE Access）第9卷（2021年）：89181-89197。