Hierarchical Contrast for Unsupervised Skeleton-Based Action Representation Learning

Authors: Jianfeng Dong, Shengkai Sun, Zhonglin Liu, Shujie Chen, Baolong Liu, Xun Wang

AAAI 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments on four datasets, i.e., NTU60, NTU-120, PKU-I and PKU-II, show that Hi Co achieves a new state-of-the-art for unsupervised skeleton-based action representation learning in two downstream tasks including action recognition and retrieval, and its learned action representation is of good transferability. Besides, we also show that our framework is effective for semi-supervised skeleton-based action recognition.
Researcher Affiliation Academia 1College of Computer Science and Technology, Zhejiang Gongshang University, China 2Zhejiang Key Lab of E-Commerce, China
Pseudocode No No pseudocode or algorithm blocks were found in the paper.
Open Source Code Yes Our code is available at https://github.com/Hui Guan Lab/Hi Co.
Open Datasets Yes Experiments are conducted on four popular skeleton-based action datasets, i.e., NTU-60 (Shahroudy et al. 2016), NTU-120 (Liu et al. 2019), PKU-I, and PKU-II (Liu et al. 2020).
Dataset Splits Yes On NTU-60 and NTU-120, we follow two standard evaluation protocols: cross-subject (xsub), and cross-view (x-view). Following (Lin et al. 2020), we report the x-sub results on PKU I and II.
Hardware Specification No No specific hardware (e.g., GPU model, CPU, memory) used for experiments was mentioned.
Software Dependencies No No specific software dependencies with version numbers were mentioned.
Experiment Setup No The paper does not provide specific hyperparameters like learning rate, batch size, or optimizer settings for the experimental setup.