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

We propose a novel attentive sequence to sequence translator (ASST) for cliplocalization in videos by natural language descriptions. We make twocontributions. First, we propose a bi-directional Recurrent Neural Network(RNN) with a finely calibrated vision-language attentive mechanism tocomprehensively understand the free-formed natural language descriptions. TheRNN parses natural language descriptions in two directions, and the attentivemodel attends every meaningful word or phrase to each frame, thereby resultingin a more detailed understanding of video content and description semantics.Second, we design a hierarchical architecture for the network to jointly modellanguage descriptions and video content. Given a video-description pair, thenetwork generates a matrix representation, i.e., a sequence of vectors. Eachvector in the matrix represents a video frame conditioned by the description.The 2D representation not only preserves the temporal dependencies of framesbut also provides an effective way to perform frame-level video-languagematching. The hierarchical architecture exploits video content with multiplegranularities, ranging from subtle details to global context. Integration ofthe multiple granularities yields a robust representation for multi-levelvideo-language abstraction. We validate the effectiveness of our ASST on twolarge-scale datasets. Our ASST outperforms the state-of-the-art by $4.28\%$ inRank$@1$ on the DiDeMo dataset. On the Charades-STA dataset, we significantlyimprove the state-of-the-art by $13.41\%$ in Rank$@1,IoU=0.5$.

Attentive Sequence to Sequence Translation for Localizing Clips of Interest by Natural Language Descriptions