Label distribution learning with label-specific features

Authors: Tingting Ren, Xiuyi Jia, Weiwei Li, Lei Chen, Zechao Li

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

Reproducibility Variable Result LLM Response
Research Type Experimental The experimental results on several real-world data sets validate the effectiveness of our method. (Abstract)
Researcher Affiliation Academia 1School of Computer Science and Engineering, Nanjing University of Science and Technology, China 2Jiangsu Key Laboratory of Big Data Security & Intelligent Processing, Nanjing University of Posts and Telecommunications, China 3State Key Laboratory for Novel Software Technology, Nanjing University, China 4College of Astronautics, Nanjing University of Aeronautics and Astronautics, China
Pseudocode Yes Algorithm 1: The LDLSF Framework (Section 3.2)
Open Source Code No The paper does not contain any statement about releasing its code, nor any links to a code repository. The phrase 'All the codes are shared by original authors' refers to competitor algorithms, not their own.
Open Datasets Yes We execute our experiments on five label distribution data sets, including two facial expression data sets s-JAFFE and SBU 3DFE [Geng, 2016], and three image sentiment data sets, i.e., Emotion6 [Peng et al., 2015], Flickr LDL and Twitter LDL [Yang et al., 2017b]. (Section 4.1)
Dataset Splits Yes On each data set, ten times ten-folds cross-validation is conducted and the mean value and standard deviation of each evaluation criterion is recorded. (Section 4.4) tune the trade-off parameters from 10{ 4, 3, ,2,3} for LDL-SCL and tune the parameters from 2{10, 9, ,9,10} for LLSF-LDL using ten-fold cross-validation. (Section 4.3)
Hardware Specification No The paper does not provide any specific hardware details (e.g., CPU, GPU models, or memory) used for running its experiments.
Software Dependencies No The paper mentions methods like ADMM, L-BFGS, and PCA but does not provide specific version numbers for any software libraries or dependencies used in their implementation.
Experiment Setup Yes In LDLSF, the parameters λ1, λ2 and λ3 are selected from 10{ 6, 5, , 2, 1}, respectively, and ρ is simply set as 10 3. Besides, Q is initialized by the identity matrix. Both W and M are diagonal matrices in which all diagonal elements are 0.5. The initialization of other variables is all-zero. (Section 4.3)