Low-Rank Tensor Completion with Spatio-Temporal Consistency

Authors: Hua Wang, Feiping Nie, Heng Huang

AAAI 2014 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Our method shows promising results in all evaluations on both 3D biomedical image sequence and video benchmark data sets.
Researcher Affiliation Academia Department of Electrical Engineering and Computer Science Colorado School of Mines, Golden, Colorado 80401, USA Department of Computer Science and Engineering University of Texas at Arlington, Arlington, Texas 76019, USA
Pseudocode Yes Algorithm 3: Algorithm to solve the problem (9).
Open Source Code No The paper does not provide concrete access to source code for the methodology described.
Open Datasets No The paper mentions using "3D MRI images" and "Foreman data and Flower data" but does not provide specific links, DOIs, repository names, or formal citations for public access to these datasets.
Dataset Splits No The paper describes corrupting data (e.g., removing 70% pixels) to simulate missing values but does not provide specific training, validation, or test dataset splits.
Hardware Specification No The paper does not provide specific hardware details (e.g., GPU/CPU models, memory amounts) used for running its experiments.
Software Dependencies No The paper describes algorithms and methods (e.g., ADM, APG, LRTC, Tucker) but does not provide specific software dependencies with version numbers (e.g., library names with versions).
Experiment Setup Yes In our experiments, we set the parameter α in Eq. (9) as 1 for simplicity. Given the input tensor X, we empirically set the error bound ε = 0.05 P ijk |xijk|/ (r c n).