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

Self-attention based Transformer has achieved great success in many computervision tasks. However, its application to video quality assessment (VQA) hasnot been satisfactory so far. Evaluating the quality of in-the-wild videos ischallenging due to the unknown of pristine reference and shooting distortion.This paper presents a co-trained Space-Time Attention network for the VQAproblem, termed StarVQA+. Specifically, we first build StarVQA+ by alternatelyconcatenating the divided space-time attention. Then, to facilitate thetraining of StarVQA+, we design a vectorized regression loss by encoding themean opinion score (MOS) to the probability vector and embedding a specialtoken as the learnable variable of MOS, leading to better fitting of human'srating process. Finally, to solve the data hungry problem with Transformer, wepropose to co-train the spatial and temporal attention weights using bothimages and videos. Various experiments are conducted on the de-factoin-the-wild video datasets, including LIVE-Qualcomm, LIVE-VQC, KoNViD-1k,YouTube-UGC, LSVQ, LSVQ-1080p, and DVL2021. Experimental results demonstratethe superiority of the proposed StarVQA+ over the state-of-the-art.

StarVQA+: Co-training Space-Time Attention for Video Quality Assessment