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

Although CNN has reached satisfactory performance in image-related tasks,using CNN to process videos is much more challenging due to the enormous sizeof raw video streams. In this work, we propose to use motion vectors andresiduals from modern video compression techniques to effectively learn therepresentation of the raw frames and greatly remove the temporal redundancy,giving a faster video processing model. Compressed Video ActionRecognition(CoViAR) has explored to directly use compressed video to train thedeep neural network, where the motion vectors were utilized to present temporalinformation. However, motion vector is designed for minimizing video size whereprecise motion information is not obligatory. Compared with optical flow,motion vectors contain noisy and unreliable motion information. Inspired by themechanism of video compression codecs, we propose an approach to refine themotion vectors where unreliable movement will be removed while temporalinformation is largely reserved. We prove that replacing the original motionvector with refined one and using the same network as CoViAR has achievedstate-of-art performance on the UCF-101 and HMDB-51 with negligible efficiencydegrades comparing with original CoViAR.

Compressed Video Action Recognition with Refined Motion Vector