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

Lack of audio-video synchronization is a common problem during televisionbroadcasts and video conferencing, leading to an unsatisfactory viewingexperience. A widely accepted paradigm is to create an error detectionmechanism that identifies the cases when audio is leading or lagging. Wepropose ModEFormer, which independently extracts audio and video embeddingsusing modality-specific transformers. Different from the othertransformer-based approaches, ModEFormer preserves the modality of the inputstreams which allows us to use a larger batch size with more negative audiosamples for contrastive learning. Further, we propose a trade-off between thenumber of negative samples and number of unique samples in a batch tosignificantly exceed the performance of previous methods. Experimental resultsshow that ModEFormer achieves state-of-the-art performance, 94.5% for LRS2 and90.9% for LRS3. Finally, we demonstrate how ModEFormer can be used for offsetdetection for test clips.

ModEFormer: Modality-Preserving Embedding for Audio-Video Synchronization using Transformers