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

Temporal Language Grounding seeks to localize video moments that semanticallycorrespond to a natural language query. Recent advances employ the attentionmechanism to learn the relations between video moments and the text query.However, naive attention might not be able to appropriately capture suchrelations, resulting in ineffective distributions where target video momentsare difficult to separate from the remaining ones. To resolve the issue, wepropose an energy-based model framework to explicitly learn moment-querydistributions. Moreover, we propose DemaFormer, a novel Transformer-basedarchitecture that utilizes exponential moving average with a learnable dampingfactor to effectively encode moment-query inputs. Comprehensive experiments onfour public temporal language grounding datasets showcase the superiority ofour methods over the state-of-the-art baselines.

DemaFormer: Damped Exponential Moving Average Transformer with Energy-Based Modeling for Temporal Language Grounding