While much research has been done in text-to-image synthesis, little work has been done to explore the usage of linguistic structure of the input text. Such information is even more important for story visualization since its inputs have an explicit
narrative structure that needs to be translated into an image sequence (or visual story). Prior work in this domain has shown that there is ample room for improvement in the generated image sequence in terms of visual quality, consistency and relevance. In this paper, we first explore the use of constituency parse trees using a Transformer-based recurrent architecture for encoding structured input. Second, we augment the structured input with commonsense information and study the impact of this external knowledge on the generation of visual story. Third, we also incorporate visual structure via bounding boxes and dense captioning to provide feedback about the characters/objects in generated images within a dual learning setup. We show that off-the-shelf dense-captioning models trained on Visual Genome can improve the spatial structure of images from a different target domain without needing fine-tuning. We train the model end-to-end using intra-story contrastive loss (between words and image sub-regions) and show significant improvements in visual quality. Finally, we provide an analysis of the linguistic and visuo-spatial information.
In this paper we present TeMoTopic, a visualization component for temporal exploration of topics in text corpora. TeMoTopic uses the temporal mosaic metaphor to present topics as a timeline of stacked bars along with related keywords for each topic.
The visualization serves as an overview of the temporal distribution of topics, along with the keyword contents of the topics, which collectively support detail-on-demand interactions with the source text of the corpora. Through these interactions and the use of keyword highlighting, the content related to each topic and its change over time can be explored.
This research aimed to create a Suggested Imagination to active the roll of the
Strategic Planning that the initial stage Schools headmasters in Damascus must use to
manage the educational crises in their institution.
The research society contain
all the initial stage schools headmaster in Damascus
City, that they are (316) headmasters, and the research was implicated on a random sample
contain (242) member.
The researcher depended on the analytical descriptive method, and used a
questionnaire to collect information, so he repaired two questionnaires, the first one about
the most crises the initial stage schools suffer, and the second contains (58) items about the
proceedings which the headmaster must do them, and it divided to for fields, they are:
before the happened of the crisis, planning to management the crisis, management the
crises, the prevention and the capitalize of the crises after it happened.
The results showed that the initial stage Schools headmasters are suffering from
crises related to the students, the curriculum, and the teachers, and their practice degree for
the subtrahend proceedings quadrated to the questionnaire is a median degree, that is
subpoenaed drawing up a suggested imagination to become the Strategic Planning is the
method which used to manage the educational crises and obviated them.
ربط الدارسون العرب من فلاسفة وأصوليين و لغويين و بلاغيين بين المعنى
و الصورة الذهنية، فقد رأوا أن المعنى هو الصورة الذهنية التي وضعت بإزائها
الألفاظ و قد كان لابد لفهم مسألة المعنى من أن تُدرس الصورة الذهنية و تُظهر علاقتها بإدراك الواقع الخارجي، و
صلتها باللغة المعبرة عن هذه الصورة، و في هذا البحث محاولة لفهم الصورة الذهنية لدى الدارسين العرب القدماء، و كان لابد للوصول إلى هذا الفهم من إطلالة سريعة على مفهوم الصورة الذهنية لدى الغربيين لتتضح صورتها، و تُفهم في تصورها لدى العرب، و لم يحاول البحث المقارنة بين المفهومين بقدر ما حاول إعطاء تصور كل من الفريقين لهذه المسألة.
