A Local Sparse Model for Matching Problem

Authors: Bo Jiang, Jin Tang, Chris Ding, Bin Luo

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

Reproducibility Variable Result LLM Response
Research Type Experimental Promising experimental results show the effectiveness of the proposed LSM method. In this section, we apply LSM to some matching tasks. We compare our LSM with the match selection method SM (Leordeanu and Hebert 2005), Game M (Albarelli et al. 2009), and Enet M (Rodol a et al. 2013).
Researcher Affiliation Academia 1School of Computer Science and Technology, Anhui University, Hefei, 230601, China 2CSE Department, University of Texas at Arlington, Arlington, TX 76019, USA
Pseudocode No The paper describes an iterative update rule in equation form (Eq. 8) and prose in the 'Computational algorithm' section, but it does not present it as a structured pseudocode block or algorithm.
Open Source Code No No explicit statement or link providing access to the source code for the methodology was found.
Open Datasets Yes Following the experimental setting (Cho, Lee, and Lee 2010; Leordeanu and Hebert 2005), we have randomly generated data sets of n M 2D model point set M. In this section, we perform feature matching on CMU and YORK sequences (Zhou and la Torre 2012; Cho, Lee, and Lee 2010; Luo and Hancock 2001).
Dataset Splits No No specific details about training, validation, or test dataset splits (e.g., percentages, sample counts, or explicit mention of 'validation set') were provided, beyond describing how data was generated or selected for evaluation.
Hardware Specification No No specific hardware details such as GPU/CPU models, processor types, or memory amounts used for running experiments were mentioned in the paper.
Software Dependencies No No specific software dependencies with version numbers were mentioned in the paper.
Experiment Setup Yes The affinity matrix W is computed by Wij,kl = exp( r D ik r M jl 2 F /σr), where σr was set to 0.05 in this experiment, and r D ik is the Euclidean. Firstly, set threshold δt = 0.001 mean(X(t)).