Visual Sentiment Analysis aims to understand how images affect people, in terms of evoked emotions. Although this field is rather new, a broad range of techniques have been …
Matching pedestrians across multiple camera views known as human re-identification (re- identification) is a challenging problem in visual surveillance. In the existing works …
M Malinowski, M Fritz - Advances in neural information …, 2014 - proceedings.neurips.cc
We propose a method for automatically answering questions about images by bringing together recent advances from natural language processing and computer vision. We …
We study the problem of object classification when training and test classes are disjoint, ie no training examples of the target classes are available. This setup has hardly been studied …
Emotions can be evoked in humans by images. Most previous works on image emotion analysis mainly used the elements-of-art-based low-level visual features. However, these …
J Machajdik, A Hanbury - Proceedings of the 18th ACM international …, 2010 - dl.acm.org
Images can affect people on an emotional level. Since the emotions that arise in the viewer of an image are highly subjective, they are rarely indexed. However there are situations …
Hundreds of thousands of photographs are uploaded to the internet every minute through various social networking and photo sharing platforms. While some images get millions of …
Object recognition systems constitute a deeply entrenched and omnipresent component of modern intelligent systems. Research on object recognition algorithms has led to advances …
Color names are required in real-world applications such as image retrieval and image annotation. Traditionally, they are learned from a collection of labeled color chips. These …