The purpose of visual media is to convey information, ideas, concepts and emotions, and for this reason, the effectiveness of visual media can be assessed by how much it captures the attention and engages with its audience. Eye movement patterns have long been recognised as providing valuable insights into the cognitive processes that underlie attention, learning and memory, and as such they may shed light on how viewers engage with visual media. The process of measuring and analysing the movements of a person's eyes is called eye-gaze tracking, which is a powerful tool with a broad range of applications, not only in studying how people interact with visual content, but also in domains such as healthcare, driving, gaming, and many others. Thanks to advancements in technology, modern eye-gaze trackers have evolved into much less intrusive and more comfortable devices than their scary predecessors. This has also worked in their favour in making eye-gaze trackers, whether screen-based, head-mounted, or embedded within VR headsets, more accessible and easy to use. In view of the increasing popularity in using eye-gaze tracking to study attention and engagement, this tutorial aims to explore this technology from different angles, including its development over the years, its technical workings, the metrics that may be used to quantify visual attention, and several application domains.

In recent years, Page Object Detection (POD) has become a popular document understanding task, proving to be a non-trivial task given the potential complexity of documents. The rise of neural networks facilitated a more general learning approach to this task. However, in the literature, the different objects such as formulae, or figures among others, are generally considered individually. In this paper, we describe the joint localisation of six object classes relevant to scientific papers, namely isolated formulae, embedded formulae, figures, tables, variables and references. Through a qualitative analysis of these object classes, we note a hierarchy among the classes and propose a new localisation approach, using two, cascaded You Only Look Once (YOLO) networks. We also present a new data set consisting of labelled bounding boxes for all six object classes. This data set combines two commonly used data sets in the literature for formulae localisation, adding to the document images in these data sets the labels for figures, tables, variables and references. Using this data set, we achieve an average F1-score of 0.755 across all classes, which is comparable to the state-of-the-art for the object classes when considered individually for localisation.

Controlling the distribution of sensitive content such as pornography has become paramount with the ever-growing accessibility to the internet. Manual filtering of such large volumes of data is practically impossible, thus, the automatic detection of said material is sought after by Law Enforcement Agencies (LEAs) and has been tackled in various manners. However, the sorting of flagged pornographic documents is still done manually using scales that describe hierarchical degrees of content severity. In this paper, we address pornography detection by creating a model capable of locating and labelling sexual organs in images and extend this model to perform image classification to provide the user with one of 19 semantically meaningful descriptors of the content. Generating these descriptors serves as a proof of concept before approaching LEAs to work with illegal CSA material and scales such as COPINE. After creating our own custom sexual organ object detection dataset for the task at hand, we achieved an object detection mean average precision score of 63.63% and a top-3 classification accuracy of 87.78%.

Hyperspectral imaging (HSI) is used in analysis of paintings to obtain features hidden to the human eye by selecting specific wavelengths. Superpixel segmentation can be applied to HSI for feature extraction. A superpixel algorithm processes an image in a way in which the result includes an unnecessary amount of over-segmentation. In this work, we use over-segmentation and propose Spectral Similarity Merging (SSM), a region growing algorithm based on homogeneous spectral properties with the aim to reduce over-segmentation without compromising under-segmentation. The algorithm focuses on the similarity of the spectral shapes rather than intensity. Results show an average of 45% reduction in over-segmentation and an average of 53% improvement on the F-score on existing superpixel segmentation algorithms.

Within the context of eye-gaze tracking, the capability of permitting the user to move naturally is an important step towards allowing for more natural user interaction in less constrained scenarios. Natural movement can be characterised by changes in head pose, as well as non-rigid face deformations as the user performs different facial expressions. While the estimation of head pose within the domain of eye-gaze tracking is being increasingly considered, the face is most often regarded as a rigid body. The few methods that factor the challenge of handling face deformations into the head pose estimation problem, often require the availability of a pre-defined face model or a considerable amount of training data. In this paper, we direct our attention towards the application of shape-and-motion factorisation for head pose estimation, since this does not generally rely on the availability of an initial face model. Over the years, various shape-and-motion factorisation methods have been proposed to address the challenges of rigid and non-rigid shape and motion recovery, in a batch or sequential manner. However, the real-time recovery of non-rigid shape and motion by factorisation remains, in general, an open problem. Our work addresses this open problem by proposing a sequential factorisation method for non-rigid shape and motion recovery, which does not rely on the availability of a pre-defined face deformation model or training data. Quantitative and qualitative results show that our method can handle various non-rigid face deformations without deterioration of the head pose estimation accuracy.

Digital copies of musical scores may be saved on tablet devices, compressing volumes of scores into a single portable device. Tablet screens are however typically smaller than printed sheet music such that the score needs to be resized for readability. This necessitates additional page turning which is made more complex when repeat instructions are used since these give rise to forward and backward page turns of the music. In this paper, we tackle this problem by first performing image analysis of the score in order to identify repeat instructions and hence flatten the score. Thus, the music player is presented the score as it should be played. We then propose the use of eye-gaze tracking to provide a hands-free page turning mechanism. Thus, the player remains in full control of when the page turn occurs. Through a preliminary study, we found that our proposed score flattening and eye-gaze page turning reduced the time spent navigating the page turns by 47% in comparison to available music score reading tools.