… a spherical convolution-empowered FoV prediction method, which is a multi-source
prediction … A spherical convolutional neural network is used instead of a traditional two-dimensional …

… Existing studies based on planar convolutional neural network (CNN) suffer from the image
… the sphere-to-plane projection. In this paper, we start by proposing a spherical convolution …

… and past viewports, we develop a single viewport prediction model using convolutional neural
… viewport area in the whole spherical image. Following the correlation filters with weighted …

… on the predicted heatmap. We propose a convolutional LSTM[1] based model to predict the
… precoded into different viewports covering different portions of the sphere surface. Based on …

… we propose a novel viewport prediction model to address viewport prediction as a time series
forecasting problem. Unlike … Sun, “A spherical convolution approach for learning long term …

… To solve this, we add 4 convolution layer after the attention model to extend the intra-frame
salient information to the entire receptive field. Through this operation, our model can make a …

… through deformable convolutions to eliminate 2D-to-Sphere intrinsic sampling distortions
and use multilayer perceptron to predict score of the whole sphere. The final prediction score is …

… a spherical convolution-empowered FoV prediction method, which is a multi-source prediction
… Jiang, “A viewport prediction framework for panoramic videos,” in 2020 International Joint …

… Thus, this paper proposes a viewportbased convolutional … tasks of viewport proposal and
viewport saliency prediction. … the spherical CNN [5] in our VP-net to extract spherical features…

… for single viewport prediction with polling layers are dropped and more convolution layers
… video coding based on projection format adaptation and spherical neighboring relationship. …