Visual representation of negation: Real world data analysis on comic image design
This addresses a problem in cognitive science and AI by showing how visual negation works in comics, though it is incremental in exploring real-world data.
The study challenged the view that visual representations cannot depict negation by analyzing comic illustrations, finding that some comics convey negation without sequences or symbols, but deep learning models struggled to classify these images as effectively as humans.
There has been a widely held view that visual representations (e.g., photographs and illustrations) do not depict negation, for example, one that can be expressed by a sentence "the train is not coming". This view is empirically challenged by analyzing the real-world visual representations of comic (manga) illustrations. In the experiment using image captioning tasks, we gave people comic illustrations and asked them to explain what they could read from them. The collected data showed that some comic illustrations could depict negation without any aid of sequences (multiple panels) or conventional devices (special symbols). This type of comic illustrations was subjected to further experiments, classifying images into those containing negation and those not containing negation. While this image classification was easy for humans, it was difficult for data-driven machines, i.e., deep learning models (CNN), to achieve the same high performance. Given the findings, we argue that some comic illustrations evoke background knowledge and thus can depict negation with purely visual elements.