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

Audio-Visual Event Localization (AVEL) is the task of temporally localizingand classifying \emph{audio-visual events}, i.e., events simultaneously visibleand audible in a video. In this paper, we solve AVEL in a weakly-supervisedsetting, where only video-level event labels (their presence/absence, but nottheir locations in time) are available as supervision for training. Our idea isto use a base model to estimate labels on the training data at a finer temporalresolution than at the video level and re-train the model with these labels.I.e., we determine the subset of labels for each \emph{slice} of frames in atraining video by (i) replacing the frames outside the slice with those from asecond video having no overlap in video-level labels, and (ii) feeding thissynthetic video into the base model to extract labels for just the slice inquestion. To handle the out-of-distribution nature of our synthetic videos, wepropose an auxiliary objective for the base model that induces more reliablepredictions of the localized event labels as desired. Our three-stage pipelineoutperforms several existing AVEL methods with no architectural changes andimproves performance on a related weakly-supervised task as well.

Temporal Label-Refinement for Weakly-Supervised Audio-Visual Event Localization