This study proposes a video retargeting method using deep neural network-based object detection. First, the meaningful regions of the input video denoted by ...

Currently, as the mainstream methods, target detection based on deep learning is mainly divided into two categories, including two-stage detection methods and ...

We propose a spatiotemporal consistency-enhanced network (STCEN) to highlight the disturbances of abnormal data from both spatial and temporal aspects.

As for post-processing-based methods, they optimize the detection result through the spatio-temporal consistency of the video target. When the image quality ...