Small Face Detection with Deep Learning Approaches
MetadataShow full item record
This thesis considers small face detection in uncontrolled environments and develops robust deep learning approaches for this challenging problem. A novel multi-scale face detector is developed by integrating novel anchor design, efficient regression loss and additional detection layers. Several multi-scale dense convolutional networks are developed to boost up the detection of small faces. Experimental results on public face databases demonstrate that the proposed methods outperform the state-of-the-art methods (e.g. YOLOv3) for detection of small faces.
Showing items related by title, author, creator and subject.
Searching for Differences in Race: Is There Evidence for Preferential Detection of Other-Race Faces?Lipp, Ottmar; Terry, D.; Smith, J.; Tellegen, C.; Kuebbeler, J.; Newey, M. (2009)Previous research has suggested that like animal and social fear-relevant stimuli, other-race faces (African American) are detected preferentially in visual search. Three experiments using Chinese or Indonesian faces as ...
Liang, A.; Wang, C.; Liu, Wan-Quan; Li, L. (2016)In this paper, we propose a robust facial landmarking scheme for frontal faces which can be applied on both controlled and uncontrolled environ-ment. This scheme is based on improvement/extension of the tree-structured ...
Chloroplast DNA diversity associated with protected slopes and valleys for hybridizing Eucalyptus species on isolated ranges in south-eastern AustraliaPollock, L.; Bayly, M.; Nevill, Paul; Vesk, P. (2013)Aim To relate genetic diversity to topographic features and to investigate genetic interactions between Eucalyptus species in a local centre of endemism and diversity in south-eastern Australia. Location Grampian Ranges, ...