Bicubic downscaling is a prevalent technique used to reduce the video st...
Deep neural networks are vulnerable to adversarial attacks....
Data size is the bottleneck for developing deep saliency models, because...
Data size is the bottleneck for developing deep saliency models, because...
Currently, a plethora of saliency models based on deep neural networks h...
Virtual viewpoints synthesis is an essential process for many immersive
...
Most of current studies on human gaze and saliency modeling have used
hi...