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 Tools annual

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 monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Text-video retrieval is a challenging cross-modal task, which aims to alignvisual entities with natural language descriptions. Current methods either failto leverage the local details or are computationally expensive. What's worse,they fail to leverage the heterogeneous concepts in data. In this paper, wepropose the Disentangled Conceptualization and Set-to-set Alignment (DiCoSA) tosimulate the conceptualizing and reasoning process of human beings. Fordisentangled conceptualization, we divide the coarse feature into multiplelatent factors related to semantic concepts. For set-to-set alignment, where aset of visual concepts correspond to a set of textual concepts, we propose anadaptive pooling method to aggregate semantic concepts to address the partialmatching. In particular, since we encode concepts independently in only a fewdimensions, DiCoSA is superior at efficiency and granularity, ensuringfine-grained interactions using a similar computational complexity ascoarse-grained alignment. Extensive experiments on five datasets, includingMSR-VTT, LSMDC, MSVD, ActivityNet, and DiDeMo, demonstrate that our methodoutperforms the existing state-of-the-art methods.

Text-Video Retrieval with Disentangled Conceptualization and Set-to-Set Alignment