Voronoi-Based Compact Image Descriptors: Efficient Region-of-Interest Retrieval With VLAD and Deep-Learning-Based Descriptors
Sign Up to like & getrecommendations! Published in 2017 at "IEEE Transactions on Multimedia"
DOI: 10.1109/tmm.2017.2673415
Abstract: We investigate the problem of image retrieval based on visual queries when the latter comprise arbitrary regions-of-interest (ROI) rather than entire images. Our proposal is a compact image descriptor that combines the state-of-the-art in content-based… read more here.
Keywords: descriptor; image; retrieval; voronoi based ... See more keywords
COMIC: Toward A Compact Image Captioning Model With Attention
Sign Up to like & getrecommendations! Published in 2019 at "IEEE Transactions on Multimedia"
DOI: 10.1109/tmm.2019.2904878
Abstract: Recent works in image captioning have shown very promising raw performance. However, we realize that most of these encoder–decoder style networks with attention do not scale naturally to large vocabulary size, making them difficult to… read more here.
Keywords: image captioning; attention; compact image; model ... See more keywords