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

The Multimedia and Computer Vision Lab of the University of Augsburgparticipated in the VTT task only. We use the VATEX and TRECVID-VTT datasetsfor training our VTT models. We base our model on the Transformer approach forboth of our submitted runs. For our second model, we adapt the X-LinearAttention Networks for Image Captioning which does not yield the desired bumpin scores. For both models, we train on the complete VATEX dataset and 90% ofthe TRECVID-VTT dataset for pretraining while using the remaining 10% forvalidation. We finetune both models with self-critical sequence training, whichboosts the validation performance significantly. Overall, we find that traininga Video-to-Text system on traditional Image Captioning pipelines delivers verypoor performance. When switching to a Transformer-based architecture ourresults greatly improve and the generated captions match better with thecorresponding video.

Extended Self-Critical Pipeline for Transforming Videos to Text (TRECVID-VTT Task 2021) -- Team: MMCUniAugsburg