Predicting memorability of images using attention-driven spatial pooling and image semantics
作者：
Highlights：
• We examine the role of visual attention and image semantics in understanding image memorability.
• We propose an attention-driven spatial pooling strategy for image memorability.
• Considering image features from the salient parts of images improves the results of the previous models.
• We also investigate different semantic properties of images.
• Combining attention-driven pooling with semantic features yields state-of-the-art results.
摘要
•We examine the role of visual attention and image semantics in understanding image memorability.•We propose an attention-driven spatial pooling strategy for image memorability.•Considering image features from the salient parts of images improves the results of the previous models.•We also investigate different semantic properties of images.•Combining attention-driven pooling with semantic features yields state-of-the-art results.
论文关键词：Image understanding,Image memorability,Visual saliency,Spatial pooling,Semantic features
论文评审过程：Received 8 November 2014, Revised 1 July 2015, Accepted 20 July 2015, Available online 4 August 2015, Version of Record 25 August 2015.
论文官网地址：https://doi.org/10.1016/j.imavis.2015.07.001
