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

Effectively extracting inter-frame motion and appearance information isimportant for video frame interpolation (VFI). Previous works either extractboth types of information in a mixed way or elaborate separate modules for eachtype of information, which lead to representation ambiguity and low efficiency.In this paper, we propose a novel module to explicitly extract motion andappearance information via a unifying operation. Specifically, we rethink theinformation process in inter-frame attention and reuse its attention map forboth appearance feature enhancement and motion information extraction.Furthermore, for efficient VFI, our proposed module could be seamlesslyintegrated into a hybrid CNN and Transformer architecture. This hybrid pipelinecan alleviate the computational complexity of inter-frame attention as well aspreserve detailed low-level structure information. Experimental resultsdemonstrate that, for both fixed- and arbitrary-timestep interpolation, ourmethod achieves state-of-the-art performance on various datasets. Meanwhile,our approach enjoys a lighter computation overhead over models with closeperformance. The source code and models are available athttps://github.com/MCG-NJU/EMA-VFI.

Extracting Motion and Appearance via Inter-Frame Attention for Efficient Video Frame Interpolation