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/

Zendy Plus

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

Zendy Tools

Zendy Open

Recently, convolutional networks (convnets) have proven useful for predictingoptical flow. Much of this success is predicated on the availability of largedatasets that require expensive and involved data acquisition and laborious la-beling. To bypass these challenges, we propose an unsuper- vised approach(i.e., without leveraging groundtruth flow) to train a convnet end-to-end forpredicting optical flow be- tween two images. We use a loss function thatcombines a data term that measures photometric constancy over time with aspatial term that models the expected variation of flow across the image.Together these losses form a proxy measure for losses based on the groundtruthflow. Empiri- cally, we show that a strong convnet baseline trained with theproposed unsupervised approach outperforms the same network trained withsupervision on the KITTI dataset.

Back to Basics: Unsupervised Learning of Optical Flow via Brightness Constancy and Motion Smoothness