Deeply fusing multi-model quality-aware features for sophisticated human activity understanding

作者：

Highlights：

• We propose a novel action recognition framework towards sophisticated activity understanding.

• We design a multi-channel feature fusion (MCFF) algorithm to capture visual appearance, motion and acoustic patterns from each video frame.

摘要

•We propose a novel action recognition framework towards sophisticated activity understanding.•We design a multi-channel feature fusion (MCFF) algorithm to capture visual appearance, motion and acoustic patterns from each video frame.

论文关键词：Human action recognition,Image quality correlation,Multi-channel feature fusion,Video retrieval

论文评审过程：Received 26 May 2019, Revised 20 January 2020, Accepted 7 February 2020, Available online 2 March 2020, Version of Record 5 March 2020.

论文官网地址：https://doi.org/10.1016/j.image.2020.115809