Human pose search using deep networks

作者：

Highlights：

• For human pose search, two novel pose descriptors (D-I and D-II) are proposed.

• D-I pools scores of deep poselets (body part detectors in a specific pose).

• D-II, maps an image such that similar and dissimilar pose images are separated.

• Both descriptors use CNNs and do not need an explicit human pose estimation.

• These have been shown to outperform other pose descriptors by large margins.

摘要

•For human pose search, two novel pose descriptors (D-I and D-II) are proposed.•D-I pools scores of deep poselets (body part detectors in a specific pose).•D-II, maps an image such that similar and dissimilar pose images are separated.•Both descriptors use CNNs and do not need an explicit human pose estimation.•These have been shown to outperform other pose descriptors by large margins.

论文关键词：Pose retrieval,Pose estimation,Video and image retrieval,Deep networks

论文评审过程：Received 30 September 2015, Revised 19 September 2016, Accepted 12 December 2016, Available online 23 December 2016, Version of Record 3 January 2017.

论文官网地址：https://doi.org/10.1016/j.imavis.2016.12.002