Learning Distance for Sequences by Learning a Ground Metric

Authors: Bing Su, Ying Wu

ICML 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experiments on several sequence datasets demonstrate the effectiveness and efficiency of our method.
Researcher Affiliation Academia 1Science & Technology on Integrated Information System Laboratory, Institute of Software, Chinese Academy of Sciences, Beijing, China 2Department of Electrical and Computer Engineering, Northwestern University, Evanston, IL, USA.
Pseudocode Yes Algorithm 1 RVSML
Open Source Code No The paper does not provide a specific link or explicit statement about the public availability of its source code.
Open Datasets Yes MSR Action3D dataset (Li et al., 2010) contains 567 depth video sequences from 20 action classes.
Dataset Splits Yes We follow the splits in (Wang et al., 2012; Wang & Wu, 2013) to divide the dataset into training and testing sets.
Hardware Specification No The paper does not provide specific hardware details (e.g., CPU, GPU models, or memory specifications) used for running the experiments.
Software Dependencies No The paper does not provide specific software dependencies with version numbers (e.g., Python, PyTorch versions) needed to replicate the experiment.
Experiment Setup Yes The parameters λ1, λ2, and σ of OPW are fixed to 10, 0.1 and 12, respectively, on the MSR Activity3D dataset, and 50, 0.1 and 1, respectively, on other datasets, as suggested in (Su & Hua, 2018)... For RVSML, we select m in the range of 2 to 8 with an interval of 2 and set β to a small value via cross-validation.