Traditionally, touchscreen typing has been studied in terms of motor performance. However, recent research has exposed a decisive role of visual attention being shared between the keyboard and the text area. Strategies for this are known to adapt to the task, design, and user. In this paper, we propose a unifying account of touchscreen typing, regarding it as optimal supervisory control. Under this theory, rules for controlling visuo-motor resources are learned via exploration in pursuit of maximal typing performance. The paper outlines the control problem and explains how visual and motor limitations affect it. We then present a model, implemented via reinforcement learning, that simulates co-ordination of eye and finger movements. Comparison with human data affirms that the model creates realistic finger- and eye-movement patterns and shows human-like adaptation. We demonstrate the model’s utility for interface development in evaluating touchscreen keyboard designs.

People counting in high density crowds is emerging as a new frontier in crowd video surveillance. Crowd counting in high density crowds encounters many challenges, such as severe occlusions, few pixels per head, and large variations in person's head sizes. In this paper, we propose a novel Density Independent and Scale Aware model (DISAM), which works as a head detector and takes into account the scale variations of heads in images. Our model is based on the intuition that head is the only visible part in high density crowds. In order to deal with different scales, unlike off-the-shelf Convolutional Neural Network (CNN) based object detectors which use general object proposals as inputs to CNN, we generate scale aware head proposals based on scale map. Scale aware proposals are then fed to the CNN and it renders a response matrix consisting of probabilities of heads. We then explore non-maximal suppression to get the accurate head positions. We conduct comprehensive experiments on two benchmark datasets and compare the performance with other state-of-theart methods. Our experiments show that the proposed DISAM outperforms the compared methods in both frame-level and pixel-level comparisons.

In advertising, identifying the content safety of web pages is a significant concern since advertisers do not want brands to be associated with threatening content. At the same time, publishers would like to maximize the number of web pages on which they can place ads. Thus, a fine balance must be achieved while classifying content safety in order to satisfy both advertisers and publishers. In this paper, we propose a multimodal machine learning framework that fuses visual and textual information from web pages to improve current predictions of content safety. The primary focus is on late fusion, which involves combining final model outputs of separate modalities, such as images and text, to arrive at a single decision. This paper presents a fully automated machine learning framework that performs binary and multilabel classification using late fusion techniques. We also introduce additional work in early fusion, which involves extracting and fusing intermediate features from the two separate models. Our algorithms are applied to data extracted from relevant web pages in the advertising industry. Both of our late and early fusion methods obtain significant improvements over algorithms currently in use.