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

While describing Spatio-temporal events in natural language, video captioningmodels mostly rely on the encoder's latent visual representation. Recentprogress on the encoder-decoder model attends encoder features mainly in linearinteraction with the decoder. However, growing model complexity for visual dataencourages more explicit feature interaction for fine-grained information,which is currently absent in the video captioning domain. Moreover, featureaggregations methods have been used to unveil richer visual representation,either by the concatenation or using a linear layer. Though feature sets for avideo semantically overlap to some extent, these approaches result in objectivemismatch and feature redundancy. In addition, diversity in captions is afundamental component of expressing one event from several meaningfulperspectives, currently missing in the temporal, i.e., video captioning domain.To this end, we propose Variational Stacked Local Attention Network (VSLAN),which exploits low-rank bilinear pooling for self-attentive feature interactionand stacking multiple video feature streams in a discount fashion. Each featurestack's learned attributes contribute to our proposed diversity encodingmodule, followed by the decoding query stage to facilitate end-to-end diverseand natural captions without any explicit supervision on attributes. Weevaluate VSLAN on MSVD and MSR-VTT datasets in terms of syntax and diversity.The CIDEr score of VSLAN outperforms current off-the-shelf methods by $7.8\%$on MSVD and $4.5\%$ on MSR-VTT, respectively. On the same datasets, VSLANachieves competitive results in caption diversity metrics.

Variational Stacked Local Attention Networks for Diverse Video Captioning