Intra- and Inter-Reasoning Graph Convolutional Network for Saliency Prediction on 360° Images
| العنوان: | Intra- and Inter-Reasoning Graph Convolutional Network for Saliency Prediction on 360° Images |
|---|---|
| المؤلفون: | Dongwen Chen, Chunmei Qing, Xu Lin, Mengtao Ye, Xiangmin Xu, Patrick Dickinson |
| المصدر: | IEEE Transactions on Circuits and Systems for Video Technology. 32:8730-8743 |
| بيانات النشر: | Institute of Electrical and Electronics Engineers (IEEE), 2022. |
| سنة النشر: | 2022 |
| مصطلحات موضوعية: | Media Technology, G400 Computer Science, Electrical and Electronic Engineering |
| الوصف: | Cubic projection can be utilized to divide 360° images into multiple rectilinear images, with little distortion. However, the existing saliency prediction models fail to integrate semantic information of these images. In this paper, we address this by proposing an intra- and inter-reasoning graph convolutional network for saliency prediction on 360 ° images (SalReGCN360). The whole framework contains six sub-networks, each of which contains two branches. In the training phase, after utilizing Multiple Cubic Projection (MCP), six rectilinear images are simultaneously put into corresponding sub-networks. In one of the branches, the global features of a single rectilinear image are extracted by the intra-graph inference module to finely predict local saliency of 360 ° images. In the other branch, the contextual features are extracted by the inter-graph inference module to effectively integrate semantic information of six rectilinear images. Finally, the feature maps are generated by the two branches fusion, and six corresponding rectilinear saliency maps are predicted. Extensive experiments on two popular saliency datasets illustrate the superiority of the proposed model, especially the improvement in KLD metric. |
| وصف الملف: | application/pdf |
| تدمد: | 1558-2205 1051-8215 |
| الوصول الحر: | https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3a53cc7b40a89914781255716019f343Test https://doi.org/10.1109/tcsvt.2022.3197159Test |
| حقوق: | OPEN |
| رقم الانضمام: | edsair.doi.dedup.....3a53cc7b40a89914781255716019f343 |
| قاعدة البيانات: | OpenAIRE |
| تدمد: | 15582205 10518215 |
|---|