Tased-net: Temporally-aggregating spatial encoder-decoder network for video saliency detection

K Min, JJ Corso - Proceedings of the IEEE/CVF International …, 2019 - openaccess.thecvf.com
TASED-Net is a 3D fully-convolutional network architecture for video saliency detection. It
consists of two building blocks: first, the encoder network extracts low-resolution …

Video saliency forecasting transformer

C Ma, H Sun, Y Rao, J Zhou, J Lu - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
Video saliency prediction (VSP) aims to imitate eye fixations of humans. However, the
potential of this task has not been fully exploited since existing VSP methods only focus on …

Hierarchical domain-adapted feature learning for video saliency prediction

G Bellitto, F Proietto Salanitri, S Palazzo… - International Journal of …, 2021 - Springer
In this work, we propose a 3D fully convolutional architecture for video saliency prediction
that employs hierarchical supervision on intermediate maps (referred to as conspicuity …