Learning social relation traits from face images
Refereed conference paper presented and published in conference proceedings

替代計量分析
.

其它資訊
摘要Social relation defines the association, e.g., warm, friendliness, and dominance, between two or more people. Motivated by psychological studies, we investigate if such fine grained and high-level relation traits can be characterised and quantified from face images in the wild. To address this challenging problem we propose a deep model that learns a rich face representation to capture gender, expression, head pose, and age-related attributes, and then performs pairwise-face reasoning for relation prediction. To learn from heterogeneous attribute sources, we formulate a new network architecture with a bridging layer to leverage the inherent correspondences among these datasets. It can also cope with missing target attribute labels. Extensive experiments show that our approach is effective for fine-grained social relation learning in images and videos.
著者Zhang Z., Luo P., Loy C.-C., Tang X.
會議名稱15th IEEE International Conference on Computer Vision, ICCV 2015
會議開始日11.12.2015
會議完結日18.12.2015
會議地點Santiago
會議國家/地區智利共和國
出版年份2016
月份2
日期17
卷號11-18-December-2015
頁次3631 - 3639
國際標準書號9781467383912
國際標準期刊號1550-5499
語言英式英語

上次更新時間 2020-06-08 於 02:03