Cubic-cross convolutional attention and count prior embedding for smoke segmentation

作者：

Highlights：

• We propose a Cubic-cross Convolutional Attention (CCA) in an efficient and effective way.

• We propose a count prior embedding method to extract information about the counts of smoke and non-smoke pixels.

• We propose a Cubic-cross convolutional attention and Count prior Embedding Network (CCENet) for smoke segmentation.

摘要

•We propose a Cubic-cross Convolutional Attention (CCA) in an efficient and effective way.•We propose a count prior embedding method to extract information about the counts of smoke and non-smoke pixels.•We propose a Cubic-cross convolutional attention and Count prior Embedding Network (CCENet) for smoke segmentation.

论文关键词：Smoke segmentation,Information embedding,Cubic-cross convolutional attention,Count prior attention

论文评审过程：Received 23 June 2021, Revised 25 May 2022, Accepted 13 July 2022, Available online 14 July 2022, Version of Record 21 July 2022.

论文官网地址：https://doi.org/10.1016/j.patcog.2022.108902