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

Recently, the popularity of depth-sensors such as Kinect has made depthvideos easily available while its advantages have not been fully exploited.This paper investigates, for gesture recognition, to explore the spatial andtemporal information complementarily embedded in RGB and depth sequences. Wepropose a convolutional twostream consensus voting network (2SCVN) whichexplicitly models both the short-term and long-term structure of the RGBsequences. To alleviate distractions from background, a 3d depth-saliencyConvNet stream (3DDSN) is aggregated in parallel to identify subtle motioncharacteristics. These two components in an unified framework significantlyimprove the recognition accuracy. On the challenging Chalearn IsoGD benchmark,our proposed method outperforms the first place on the leader-board by a largemargin (10.29%) while also achieving the best result on RGBD-HuDaAct dataset(96.74%). Both quantitative experiments and qualitative analysis shows theeffectiveness of our proposed framework and codes will be released tofacilitate future research.

Multi-Modality Fusion based on Consensus-Voting and 3D Convolution for Isolated Gesture Recognition