Direct Semantic Analysis for Social Image Classification

Authors: Zhiwu Lu, Liwei Wang, Ji-Rong Wen

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

Reproducibility Variable Result LLM Response
Research Type Experimental Experimental results on two benchmark image datasets show the promising performance of the proposed method.
Researcher Affiliation Academia 1School of Information, Renmin University of China, Beijing 100872, China 2Key Laboratory of Data Engineering and Knowledge Engineering, MOE, China 3Key Laboratory of Machine Perception (MOE), School of EECS, Peking University, Beijing 100871, China
Pseudocode Yes The complete DSA algorithm is outlined as follows: (1) Construct a k-NN graph... (8) Iterate Steps (4) (7) until the stopping condition is satisfied, and output the final semantically refined visual BOW representation ˆY .
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 We select two benchmark datasets for performance evaluation. The first dataset is PASCAL VOC 07 (Everingham et al. 2007)... Moreover, the second dataset is MIR FLICKR (Huiskes and Lew 2008)...
Dataset Splits Yes For the PASCAL VOC 07 dataset, we use the standard training/test split, while for the MIR FLICKR dataset we split it into 12,500 training/test images just as (Guillaumin, Verbeek, and Schmid 2010)... In the experiments, the parameters of our DSA algorithm are selected by cross-validation on the training set.
Hardware Specification Yes We run the algorithms (Matlab code) on a computer with 3GHz CPU and 32GB RAM.
Software Dependencies No The paper mentions "Matlab code" but does not specify any version numbers for Matlab or other software libraries used.
Experiment Setup Yes In the experiments, the parameters of our DSA algorithm are selected by cross-validation on the training set. For example, according to Figure 4, we set the three parameters of our DSA algorithm on the PASCAL VOC 07 dataset as: k = 25, α = 0.94 and γ = 0.00012.