Semantic Pyramids for Gender and Action Recognition
2014 (English)In: IEEE Transactions on Image Processing, ISSN 1057-7149, E-ISSN 1941-0042, Vol. 23, no 8, 3633-3645 p.Article in journal (Refereed) Published
Person description is a challenging problem in computer vision. We investigated two major aspects of person description: 1) gender and 2) action recognition in still images. Most state-of-the-art approaches for gender and action recognition rely on the description of a single body part, such as face or full-body. However, relying on a single body part is suboptimal due to significant variations in scale, viewpoint, and pose in real-world images. This paper proposes a semantic pyramid approach for pose normalization. Our approach is fully automatic and based on combining information from full-body, upper-body, and face regions for gender and action recognition in still images. The proposed approach does not require any annotations for upper-body and face of a person. Instead, we rely on pretrained state-of-the-art upper-body and face detectors to automatically extract semantic information of a person. Given multiple bounding boxes from each body part detector, we then propose a simple method to select the best candidate bounding box, which is used for feature extraction. Finally, the extracted features from the full-body, upper-body, and face regions are combined into a single representation for classification. To validate the proposed approach for gender recognition, experiments are performed on three large data sets namely: 1) human attribute; 2) head-shoulder; and 3) proxemics. For action recognition, we perform experiments on four data sets most used for benchmarking action recognition in still images: 1) Sports; 2) Willow; 3) PASCAL VOC 2010; and 4) Stanford-40. Our experiments clearly demonstrate that the proposed approach, despite its simplicity, outperforms state-of-the-art methods for gender and action recognition.
Place, publisher, year, edition, pages
Institute of Electrical and Electronics Engineers (IEEE) , 2014. Vol. 23, no 8, 3633-3645 p.
Gender recognition; action recognition; pyramid representation; bag-of-words
Electrical Engineering, Electronic Engineering, Information Engineering
IdentifiersURN: urn:nbn:se:liu:diva-110281DOI: 10.1109/TIP.2014.2331759ISI: 000340094000003PubMedID: 24956369OAI: oai:DiVA.org:liu-110281DiVA: diva2:744038
Funding Agencies|Swedish Foundation for Strategic Research through the Collaborative Unmanned Aircraft Systems Project; Swedish Research Council through the ETT Project; Strategic Area for Information and Communication Technology research ELLIIT; CADICS; Academy of Finland, through the Finnish Centre of Excellence in Computational Inference Research ; Ministerio de Ciencia e Innovacion through the Ramon y Cajal Fellowship2014-09-052014-09-052016-05-04