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

A key challenge in video enhancement and action recognition is to fuse usefulinformation from neighboring frames. Recent works suggest establishing accuratecorrespondences between neighboring frames before fusing temporal information.However, the generated results heavily depend on the quality of correspondenceestimation. In this paper, we propose a more robust solution: \emph{samplingand fusing multi-level features} across neighborhood frames to generate theresults. Based on this idea, we introduce a new module to improve thecapability of 3D convolution, namely, learnable sampling 3D convolution(\emph{LS3D-Conv}). We add learnable 2D offsets to 3D convolution which aims tosample locations on spatial feature maps across frames. The offsets can belearned for specific tasks. The \emph{LS3D-Conv} can flexibly replace 3Dconvolution layers in existing 3D networks and get new architectures, whichlearns the sampling at multiple feature levels. The experiments on videointerpolation, video super-resolution, video denoising, and action recognitiondemonstrate the effectiveness of our approach.

Learnable Sampling 3D Convolution for Video Enhancement and Action Recognition