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

Automatically describing video content with natural language has beenattracting much attention in CV and NLP communities. Most existing methodspredict one word at a time, and by feeding the last generated word back asinput at the next time, while the other generated words are not fullyexploited. Furthermore, traditional methods optimize the model using all thetraining samples in each epoch without considering their learning situations,which leads to a lot of unnecessary training and can not target the difficultsamples. To address these issues, we propose a text-based dynamic attentionmodel named TDAM, which imposes a dynamic attention mechanism on all thegenerated words with the motivation to improve the context semantic informationand enhance the overall control of the whole sentence. Moreover, the text-baseddynamic attention mechanism and the visual attention mechanism are linkedtogether to focus on the important words. They can benefit from each otherduring training. Accordingly, the model is trained through two steps: "startingfrom scratch" and "checking for gaps". The former uses all the samples tooptimize the model, while the latter only trains for samples with poor control.Experimental results on the popular datasets MSVD and MSR-VTT demonstrate thatour non-ensemble model outperforms the state-of-the-art video captioningbenchmarks.

Video Captioning with Text-based Dynamic Attention and Step-by-Step Learning