Learning Graph-based Residual Aggregation Network for Group Activity Recognition

Authors: Wei Li, Tianzhao Yang, Xiao Wu, Zhaoquan Yuan

IJCAI 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental The experimental results on two popular benchmarks for group activity recognition clearly demonstrate the superior performance of our method in comparison with the state-of-the-art methods.
Researcher Affiliation Academia Wei Li , Tianzhao Yang , Xiao Wu and Zhaoquan Yuan School of Computing and Artificial Intelligence, Southwest Jiaotong University liwei@swjtu.edu.cn, tianzhao@my.swjtu.edu.cn, wuxiaohk@gmail.com, zqyuan@swjtu.edu.cn
Pseudocode No No pseudocode or clearly labeled algorithm block is provided in the paper.
Open Source Code No No statement or link is provided indicating that the source code for the described methodology is publicly available.
Open Datasets Yes Two popular benchmarks (Volleyball Dataset (VD) [Ibrahim et al., 2016] and Collective Activity Dataset (CAD) [Choi et al., 2009]) are used to evaluate our proposed method
Dataset Splits No The paper does not explicitly provide specific percentages or sample counts for training, validation, and test splits, nor does it reference predefined splits with explicit details. It states: "randomly sampling frames from a video clip are selected as the training samples on both two datasets".
Hardware Specification No No specific hardware details (e.g., GPU or CPU models, memory specifications) used for running the experiments are mentioned in the paper.
Software Dependencies No The paper mentions "Our model is implemented based on Pytorch" but does not provide a specific version number for PyTorch or any other software dependencies.
Experiment Setup Yes The ADAM optimizer with different learning rates is used to learn the network parameters. The hyper-parameters for ADAM are set as β1 = 0.9, β2 = 0.999 and ϵ = 10 8. For the training of 40 epochs on VD, the initial learning rate is set to 1 10 4 with the dacay rate is 1/3 every 10 epochs. For the training of 30 epochs on CAD, the learning rates are set to 4 10 5 and 1 10 4 for Res Net18 and VGG16, respectively. The spatial constraint factors δ are set to 0.2, 0.3 of the image width in the training of VD and CAD, empirically. L is set to 16. The batch sizes are set to 2 on both datasets.