Connecting the Dots Using Contextual Information Hidden in Text and Images

Authors: Md Abdul Kader, Sheikh Naim, Arnold Boedihardjo, M. Shahriar Hossain

AAAI 2016 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental 3 Experimental Results
Researcher Affiliation Collaboration 1The University of Texas at El Paso, El Paso, TX 79968, Phone: (915) 747-5000 2U. S. Army Corps of Engineers, Alexandria, VA 22315
Pseudocode No No explicitly labeled pseudocode or algorithm blocks were found.
Open Source Code No No explicit statement or link regarding the public release of source code was found.
Open Datasets No The knowledge base κ = {D, Eκ, F} is constructed using images and textual context of Wikipedia pages that are related to politics and terrorism. and New York Times returns 1028 articles with the query Boston Marathon Bombing . While data sources are mentioned, there are no specific access details (link, DOI, formal citation with authors/year) for a publicly available or open dataset.
Dataset Splits No Figure 2(left) compares face recognition accuracies at different training and test rations with different combinations of techniques. The paper mentions 'training and test ratios' but does not provide specific details on the dataset splits (e.g., percentages, sample counts, or methodology) needed for reproduction.
Hardware Specification No No specific hardware details (e.g., GPU/CPU models, memory amounts, or detailed computer specifications) used for running experiments were mentioned.
Software Dependencies No The paper mentions algorithms like 'Viola-Jones algorithm' and 'pretrained convolutional neural network' but does not specify any software libraries or dependencies with version numbers.
Experiment Setup No No specific experimental setup details such as hyperparameter values, training configurations, or system-level settings were found in the main text.