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

In this paper we tackle the cross-modal video retrieval problem and, morespecifically, we focus on text-to-video retrieval. We investigate how tooptimally combine multiple diverse textual and visual features into featurepairs that lead to generating multiple joint feature spaces, which encodetext-video pairs into comparable representations. To learn theserepresentations our proposed network architecture is trained by following amultiple space learning procedure. Moreover, at the retrieval stage, weintroduce additional softmax operations for revising the inferred query-videosimilarities. Extensive experiments in several setups based on threelarge-scale datasets (IACC.3, V3C1, and MSR-VTT) lead to conclusions on how tobest combine text-visual features and document the performance of the proposednetwork. Source code is made publicly available at:https://github.com/bmezaris/TextToVideoRetrieval-TtimesV

Are All Combinations Equal? Combining Textual and Visual Features with Multiple Space Learning for Text-Based Video Retrieval