
handle: 11393/313570
Several technological developments like the Internet, mobile devices and Social Networks have spurred the sharing of images in unprecedented volumes, making tagging and commenting a common habit. Despite the recent progress in image analysis, the problem of Semantic Gap still hinders machines in fully understand the rich semantic of a shared photo. In this book, we tackle this problem by exploiting social network contributions. A comprehensive treatise of three linked problems on image annotation is presented, with a novel experimental protocol used to test eleven state-of-the-art methods. Three novel approaches to annotate, under stand the sentiment and predict the popularity of an image are presented. We conclude with the many challenges and opportunities ahead for the multimedia community.
Several technological developments like the Internet, mobile devices and Social Networks have spurred the sharing of images in unprecedented volumes, making tagging and commenting a common habit. Despite the recent progress in image analysis, the problem of Semantic Gap still hinders machines in fully understand the rich semantic of a shared photo. In this book, we tackle this problem by exploiting social network contributions. A comprehensive treatise of three linked problems on image annotation is presented, with a novel experimental protocol used to test eleven state-of-the-art methods. Three novel approaches to annotate, understand the sentiment and predict the popularity of an image are presented. We conclude with the many challenges and opportunities ahead for the multimedia community.
Image understanding, image classification, sentiment analysis, image representation
Image understanding, image classification, sentiment analysis, image representation
| selected citations These citations are derived from selected sources. This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | 0 | |
| popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network. | Average | |
| influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | Average | |
| impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network. | Average |
