Multi-tensor Completion with Common Structures

Authors: Chao Li, Qibin Zhao, Junhua Li, Andrzej Cichocki, Lili Guo

AAAI 2015 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Numerical results demonstrate that the proposed method not only outperforms state-of-the-art methods for video in-painting, but also can recover missing data well even in cases that conventional methods are not applicable.Experimental results Multi-view video in-painting with one frame lost
Researcher Affiliation Academia 1Harbin Engineering University, Harbin, Heilongjiang, China 2RIKEN Brain Science Institute, Wako, Saitama, Japan 3Systems Research Institute, PAS, Warsaw, Poland
Pseudocode Yes Pseudo-code of the algorithm is shown in Alg.1.
Open Source Code No The paper does not contain any explicit statements or links indicating that the source code for the described methodology is publicly available.
Open Datasets Yes 1http://media.au.tsinghua.edu.cn/index.jsp
Dataset Splits No The paper describes experiments where missing data is simulated at different percentages (e.g., 'randomly removed some pixels from the three videos with specific missing percentage'), but it does not specify explicit train/validation/test dataset splits for model training and evaluation.
Hardware Specification No The paper does not explicitly describe the hardware used to run its experiments.
Software Dependencies No The paper does not provide specific ancillary software details with version numbers.
Experiment Setup No The paper mentions 'tuning parameters λk,qk > 0' in Algorithm 1, but does not provide specific values for these or other typical hyperparameters such as learning rates, batch sizes, or optimizer settings used in the experiments.