Viewing Bias Matters in 360° Videos Visual Saliency Prediction

• Published in: IEEE access Vol. 11; pp. 46084 - 46094
• Main Authors: Chen, Peng-Wen, Yang, Tsung-Shan, Huang, Gi-Luen, Huang, Chia-Wen, Chao, Yu-Chieh, Lu, Chien-Hung, Wu, Pei-Yuan
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 2023; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: 360° videos; Bias; Coders; Convolutional neural networks; Datasets; Decoding; Deep learning; Feature extraction; Field of view; Prediction models; Predictive models; Recurrent neural networks; Salience; Surveillance systems; Three-dimensional displays; Video; Videos; Viewing; viewing bias; Visual saliency prediction; Visualization

360° video has been applied to many areas such as immersive contents, virtual tours, and surveillance systems. Compared to the field of view prediction on planar videos, the explosive amount of information contained in the omni-directional view on the entire sphere poses an additional challenge in p...