Code for creating semantic space models from the combination of images and text.

---------------------------------------------------------------------------

words_with_images.py: Preprocess the data, i.e: create the unique ID for the images and labels. 

phow_alg.m: Extract visual features SIFT from Images

BOVW.py: construct the Bag Of Visual Words from the output of phow_alg.m

CosineSimilarity.py: Compute semantic similarity 

MatrixCreator.py: Generate the combination model of vision-based semantics and text-based semantics