Eye landmarks detection via weakly supervised learning
作者：
Highlights：
• We propose a novel weakly supervised eye landmarks detection algorithm with object detection and recurrent learning modules.
• We introduce the pipeline of generating two format data for weakly supervised eye landmarks detection, e.g. supervised and weakly supervised data.
• The proposed method can work on facial images that are severely occluded or local view of facial images with eyes when facial landmarks detection method fails.
• Experimental results reveal our algorithm's acceptable performance of facial alignment and eye localization.
摘要
•We propose a novel weakly supervised eye landmarks detection algorithm with object detection and recurrent learning modules.•We introduce the pipeline of generating two format data for weakly supervised eye landmarks detection, e.g. supervised and weakly supervised data.•The proposed method can work on facial images that are severely occluded or local view of facial images with eyes when facial landmarks detection method fails.•Experimental results reveal our algorithm's acceptable performance of facial alignment and eye localization.
论文关键词：Eye landmarks detection,Special format data,Weakly supervised learning,Object detection,Recurrent learning module
论文评审过程：Received 7 January 2019, Revised 15 September 2019, Accepted 7 October 2019, Available online 9 October 2019, Version of Record 15 October 2019.
论文官网地址：https://doi.org/10.1016/j.patcog.2019.107076
