English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

This paper revisits recognition of natural image pleasantness by employingdeep convolutional neural networks and affordable eye trackers. There existseveral approaches to recognize image pleasantness: (1) computer vision, and(2) psychophysical signals. For natural images, computer vision approaches havenot been as successful as for abstract paintings and is lagging behind thepsychophysical signals like eye movements. Despite better results, thescalability of eye movements is adversely affected by the sensor cost. Whilethe introduction of affordable sensors have helped the scalability issue bymaking the sensors more accessible, the application of such sensors in aloosely controlled human-computer interaction setup is not yet studied foraffective image tagging. On the other hand, deep convolutional neural networkshave boosted the performance of vision-based techniques significantly in recentyears. To investigate the current status in regard to affective image tagging,we (1) introduce a new eye movement dataset using an affordable eye tracker,(2) study the use of deep neural networks for pleasantness recognition, (3)investigate the gap between deep features and eye movements. To meet theseends, we record eye movements in a less controlled setup, akin to dailyhuman-computer interaction. We assess features from eye movements, visualfeatures, and their combination. Our results show that (1) recognizing naturalimage pleasantness from eye movement under less restricted setup is difficultand previously used techniques are prone to fail, and (2) visual classcategories are strong cues for predicting pleasantness, due to theircorrelation with emotions, necessitating careful study of this phenomenon. Thislatter finding is alerting as some deep learning approaches may fit to theclass category bias.

Investigating Natural Image Pleasantness Recognition using Deep Features and Eye Tracking for Loosely Controlled Human-computer Interaction