Elisavet Chatzilari

Learn More
The fact that most users tend to tag images emotionally rather than realistically makes social datasets inherently flawed from a computer vision perspective. On the other hand they can be particularly useful due to their social context and their potential to grow arbitrary big. Our work shows how a combination of techniques operating on both tag and visual(More)
In this work we present an algorithm for extracting region level annotations from flickr images using a small set of manually labelled regions to guide the selection process. More specifically, we construct a set of flickr images that focuses on a certain concept and apply a novel graph based clustering algorithm on their regions. Then, we select the(More)
In this work we perform an extensive comparative study of approaches for mobile visual recognition by simultaneously evaluating the performance and the computational cost of state-of-the-art key-point detection, feature extraction and encoding algorithms. Every step is independently tested so that its contribution to the final computational cost can be(More)
Motivated by the widespread adoption of social networks and the abundant availability of user-generated multimedia content, our purpose in this work is to investigate how the known principles of active learning for image classification fit in this newly developed context. The process of active learning can be fully automated in this social context by(More)
Teaching the machine has been a great challenge for computer vision scientists since the very first steps of artificial intelligence. Throughout the decades there have been remarkable achievements that drastically enhanced the capabilities of the machines both from the perspective of infrastructure (i.e., computer networks, processing power, storage(More)
Our purpose in this work is to boost the performance of object classifiers learned using the self-training paradigm. We exploit the multi-modal nature of tagged images found in social networks, to optimize the process of region selection when retraining the initial model. More specifically, the proposed approach uses a small number of manually labelled(More)
Environmental data are considered of utmost importance for human life, since weather conditions, air quality and pollen are strongly related to health issues and affect everyday activities. This paper addresses the problem of discovery of air quality and pollen forecast Web resources, which are usually presented in the form of heatmaps (i.e. graphical(More)
In this work a framework for constructing object detection classifiers using weakly annotated social data is proposed. Social information is combined with computer vision techniques to automatically obtain a set of images annotated at region-detail. All assumptions made to automate the proposed framework are driven by the reasonable expectation that due to(More)
Motivated by the abundant availability of user-generated multimedia content, a data augmentation approach that enhances an initial manually labelled training set with regions from user tagged images is presented. Initially, object detection classifiers are trained using a small number of manually labelled regions as the training set. Then, a set of positive(More)
In this manuscript we present a method that leverages social media for the effortless learning of object detectors. We are motivated by the fact that the increased training cost of methods demanding manual annotation, limits their ability to easily scale in different types of objects and domains. At the same time, the rapidly growing social media(More)