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

Video captioning is a popular task that challenges models to describe eventsin videos using natural language. In this work, we investigate the ability ofvarious visual feature representations derived from state-of-the-artconvolutional neural networks to capture high-level semantic context. Weintroduce the Weighted Additive Fusion Transformer with Memory AugmentedEncoders (WAFTM), a captioning model that incorporates memory in a transformerencoder and uses a novel method, to fuse features, that ensures due importanceis given to more significant representations. We illustrate a gain inperformance realized by applying Word-Piece Tokenization and a popularREINFORCE algorithm. Finally, we benchmark our model on two datasets and obtaina CIDEr of 92.4 on MSVD and a METEOR of 0.091 on the ActivityNet CaptionsDataset.

Exploration of Visual Features and their weighted-additive fusion for Video Captioning