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

Movies provide us with a mass of visual content as well as attractingstories. Existing methods have illustrated that understanding movie storiesthrough only visual content is still a hard problem. In this paper, foranswering questions about movies, we put forward a Layered Memory Network (LMN)that represents frame-level and clip-level movie content by the Static WordMemory module and the Dynamic Subtitle Memory module, respectively.Particularly, we firstly extract words and sentences from the training moviesubtitles. Then the hierarchically formed movie representations, which arelearned from LMN, not only encode the correspondence between words and visualcontent inside frames, but also encode the temporal alignment between sentencesand frames inside movie clips. We also extend our LMN model into three variantframeworks to illustrate the good extendable capabilities. We conduct extensiveexperiments on the MovieQA dataset. With only visual content as inputs, LMNwith frame-level representation obtains a large performance improvement. Whenincorporating subtitles into LMN to form the clip-level representation, weachieve the state-of-the-art performance on the online evaluation task of'Video+Subtitles'. The good performance successfully demonstrates that theproposed framework of LMN is effective and the hierarchically formed movierepresentations have good potential for the applications of movie questionanswering.

Movie Question Answering: Remembering the Textual Cues for Layered Visual Contents