TY - JOUR
T1 - Scale coding bag of deep features for human attribute and action recognition
AU - Khan, Fahad Shahbaz
AU - van de Weijer, Joost
AU - Anwer, Rao Muhammad
AU - Bagdanov, Andrew D.
AU - Felsberg, Michael
AU - Laaksonen, Jorma
PY - 2018/1/1
Y1 - 2018/1/1
N2 - © 2017, The Author(s). Most approaches to human attribute and action recognition in still images are based on image representation in which multi-scale local features are pooled across scale into a single, scale-invariant encoding. Both in bag-of-words and the recently popular representations based on convolutional neural networks, local features are computed at multiple scales. However, these multi-scale convolutional features are pooled into a single scale-invariant representation. We argue that entirely scale-invariant image representations are sub-optimal and investigate approaches to scale coding within a bag of deep features framework. Our approach encodes multi-scale information explicitly during the image encoding stage. We propose two strategies to encode multi-scale information explicitly in the final image representation. We validate our two scale coding techniques on five datasets: Willow, PASCAL VOC 2010, PASCAL VOC 2012, Stanford-40 and Human Attributes (HAT-27). On all datasets, the proposed scale coding approaches outperform both the scale-invariant method and the standard deep features of the same network. Further, combining our scale coding approaches with standard deep features leads to consistent improvement over the state of the art.
AB - © 2017, The Author(s). Most approaches to human attribute and action recognition in still images are based on image representation in which multi-scale local features are pooled across scale into a single, scale-invariant encoding. Both in bag-of-words and the recently popular representations based on convolutional neural networks, local features are computed at multiple scales. However, these multi-scale convolutional features are pooled into a single scale-invariant representation. We argue that entirely scale-invariant image representations are sub-optimal and investigate approaches to scale coding within a bag of deep features framework. Our approach encodes multi-scale information explicitly during the image encoding stage. We propose two strategies to encode multi-scale information explicitly in the final image representation. We validate our two scale coding techniques on five datasets: Willow, PASCAL VOC 2010, PASCAL VOC 2012, Stanford-40 and Human Attributes (HAT-27). On all datasets, the proposed scale coding approaches outperform both the scale-invariant method and the standard deep features of the same network. Further, combining our scale coding approaches with standard deep features leads to consistent improvement over the state of the art.
KW - Action recognition
KW - Attribute recognition
KW - Bag of deep features
U2 - 10.1007/s00138-017-0871-1
DO - 10.1007/s00138-017-0871-1
M3 - Article
VL - 29
SP - 55
EP - 71
JO - Machine Vision and Applications
JF - Machine Vision and Applications
SN - 0932-8092
IS - 1
ER -