A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Visual learning with limited supervision
[thesis]
Preserved Fulltext
Dissertation xiii vii 5.4 Qualitative results of the text-to-image (image) retrieval for VSRN on MS-COCO dataset. We show the top-3 retrieved images for each text query, ranking from left to right. The true matches are outlined in green boxes and false matches in red boxes. We also show the attention visualization of image representation generated by VSRN under the corresponding image.
doi:10.17760/d20416794
fatcat:i4p34vooqnechmbw6qvwig3so4