Shap-Mix: Shapley Value Guided Mixing for Long-Tailed Skeleton Based Action Recognition
Authors: Jiahang Zhang, Lilang Lin, Jiaying Liu
IJCAI 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Extensive experiments on three large-scale skeleton datasets show our remarkable performance improvement under both long-tailed and balanced settings. |
| Researcher Affiliation | Academia | Jiahang Zhang , Lilang Lin , Jiaying Liu Wangxuan Institute of Computer Technology, Peking University {zjh2020, linlilang, liujiaying}@pku.edu.cn |
| Pseudocode | No | The paper does not contain a clearly labeled pseudocode or algorithm block. |
| Open Source Code | Yes | Our project is publicly available at: https://jhang2020.github.io/Projects/Shap Mix/Shap-Mix.html. |
| Open Datasets | Yes | NTU RGB+D 60 Dataset (NTU 60) [Shahroudy et al., 2016]. NTU RGB+D 120 Dataset (NTU 120) [Liu et al., 2019]. Kinetics Skeleton 400 (Kinetics 400) [Kay et al., 2017]. |
| Dataset Splits | Yes | Two evaluation protocols are recommended: a) Cross-Subject (xsub): the training data are collected from 20 subjects, while the testing data are from the other 20 subjects. b) Cross-View (xview): the front and two side captured views are used for training, while testing set includes the left and right 45-degree views. Two recommended protocols are presented: a) Cross-Subject (xsub): the training data are collected from 53 subjects, while the other 53 subjects are for testing. b) Cross-Setup (xset): the training data use even setup IDs, while testing data use odd ones. |
| Hardware Specification | No | The paper does not provide specific hardware details such as GPU models, CPU types, or memory specifications used for running experiments. |
| Software Dependencies | No | The paper mentions "CTR-GCN" as a backbone and "Open Pose toolbox" for extracting data, but does not provide specific version numbers for these or any other software dependencies (e.g., Python, PyTorch versions). |
| Experiment Setup | Yes | For the implementation of Shap-Mix, we randomly sample 2 or 3 body parts to mix in spatial dimension. The mixed temporal length is from 40% to 70% of the original length. The temperature τ is set as 0.2, and the momentum coefficient in the EMA is 0.9. The warm-up phase is for the first 5 epochs. Due to the less data in the constructed long-tailed dataset, we increase the training epochs to 100. |