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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

This paper tackles a recently proposed Video Corpus Moment Retrieval task.This task is essential because advanced video retrieval applications shouldenable users to retrieve a precise moment from a large video corpus. We proposea novel CONtextual QUery-awarE Ranking~(CONQUER) model for effective momentlocalization and ranking. CONQUER explores query context for multi-modal fusionand representation learning in two different steps. The first step derivesfusion weights for the adaptive combination of multi-modal video content. Thesecond step performs bi-directional attention to tightly couple video and queryas a single joint representation for moment localization. As query context isfully engaged in video representation learning, from feature fusion totransformation, the resulting feature is user-centered and has a largercapacity in capturing multi-modal signals specific to query. We conduct studieson two datasets, TVR for closed-world TV episodes and DiDeMo for open-worlduser-generated videos, to investigate the potential advantages of fusing videoand query online as a joint representation for moment retrieval.

CONQUER: Contextual Query-aware Ranking for Video Corpus Moment Retrieval