There is more to images than their objective physical content: for example, advertisements are created to persuade a viewer to take a certain action. We propose the novel problem of automatic advertisement understanding. To enable research on this problem, we create two datasets: an image dataset of 64,832 image ads, and a video dataset of 3,477 ads. Our data contains rich annotations encompassing the topic and sentiment of the ads, questions and answers describing what actions the viewer is prompted to take and the reasoning that the ad presents to persuade the viewer ("What should I do according to this ad, and why should I do it?"), and symbolic references ads make (e.g. a dove symbolizes peace). We also analyze the most common persuasive strategies ads use, and the capabilities that computer vision systems should have to understand these strategies. We present baseline classification results for several prediction tasks, including automatically answering questions about the messages of the ads.

Essays are frequently used as a medium for teaching and evaluating argumentation skills. Recently, there has been interest in diagrammatic outlining as a replacement to the written outline that often precedes essay writing. This paper presents a preliminary approach for automatically identifying diagram ontology elements in essays, and demonstrates its positive correlation with expert scores of essay quality.

Osteohistological studies of extant aves, and in particular the paleognaths, illuminate aspects of extinct dinosaur biology previously thought unattainable, like metabolic regime (Castanet et al., 2000;Cubo et al., 2016), biomechanics (de Ricqlès et al., 2000, and even fossil preservation rate (Marshall et al., 2021). These insights are predicated on studies demonstrating a one-to-one correspondence between arrested growth lines and chronological age (e.g., de

No abstract

No abstract