Scale coding bag of deep features for human attribute and action recognitionShow others and affiliations
2018 (English)In: Machine Vision and Applications, ISSN 0932-8092, E-ISSN 1432-1769, Vol. 29, no 1, p. 55-71Article in journal (Refereed) Published
Abstract [en]
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.
Place, publisher, year, edition, pages
SPRINGER , 2018. Vol. 29, no 1, p. 55-71
Keywords [en]
Action recognition; Attribute recognition; Bag of deep features
National Category
Computer Vision and Robotics (Autonomous Systems)
Identifiers
URN: urn:nbn:se:liu:diva-144448DOI: 10.1007/s00138-017-0871-1ISI: 000419583600005OAI: oai:DiVA.org:liu-144448DiVA, id: diva2:1176581
Note
Funding Agencies|Spanish Ministry of Science; Catalan project [2014 SGR 221]; CHISTERA project [PCIN-2015-251]; SSF [EMC2]; VR through the Strategic Area for ICT research ELLIIT [2016-05543]; Academy of Finland [251170]; Nvidia; [TIN2013-41751]; [TIN2016-79717-R]
2018-01-222018-01-222018-02-21