Learning Transferable Subspace for Human Motion Segmentation

Authors: Lichen Wang, Zhengming Ding, Yun Fu

AAAI 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments based on three human motion datasets illustrate that our approach is able to outperform state-of-the-art temporal data clustering methods.
Researcher Affiliation Academia Department of Electrical & Computer Engineering, Northeastern University, Boston, USA College of Computer & Information Science, Northeastern University, Boston, USA
Pseudocode Yes Algorithm 1. Motion Subspace Clustering
Open Source Code No The paper does not provide any explicit statements about making its own source code publicly available or provide a link to a code repository for the described methodology.
Open Datasets Yes Multi-modal Action Detection (MAD) Dataset (Huang et al. 2014) ... Keck Gesture Dataset (Jiang, Lin, and Davis 2012) ... Weizmann Dataset (Gorelick et al. 2007)
Dataset Splits No The paper mentions using '5 randomly selected sequences in source datasets' for evaluation and concatenating data for certain datasets, but it does not explicitly specify training, validation, and test dataset splits with percentages, sample counts, or a detailed splitting methodology.
Hardware Specification No The paper does not specify any hardware details (e.g., GPU models, CPU types, or memory) used for running the experiments.
Software Dependencies No The paper mentions 'HoG features (Dalal and Triggs 2005)' but does not list any specific software or library dependencies with version numbers used for its implementation.
Experiment Setup Yes The parameter values λ1 and λ2 are set to be 0.015 and 12 as the default, the correlated frame distance s = 9 and the projection size r = 80. Parameter sensitivity is analyzed later in this section.