Semantic Pyramids for Gender and Action Recognition
| Autor: | Carlo Gatta, Joost van de Weijer, Rao Muhammad Anwer, Michael Felsberg, Fahad Shahbaz Khan |
|---|---|
| Rok vydání: | 2014 |
| Předmět: |
Male
Sex Determination Analysis Biometry Computer science Feature extraction Electrical Engineering Electronic Engineering Information Engineering Machine learning computer.software_genre Sensitivity and Specificity Pattern Recognition Automated Proxemics Artificial Intelligence Minimum bounding box Image Interpretation Computer-Assisted Pyramid Humans Three-dimensional face recognition Whole Body Imaging Elektroteknik och elektronik computer.programming_language business.industry Reproducibility of Results Pattern recognition Pascal (programming language) Image Enhancement Actigraphy Computer Graphics and Computer-Aided Design Semantics Gender recognition action recognition pyramid representation bag-of-words Female Artificial intelligence business computer Algorithms Software |
| Zdroj: | IEEE Transactions on Image Processing. 23:3633-3645 |
| ISSN: | 1941-0042 1057-7149 |
| DOI: | 10.1109/tip.2014.2331759 |
| Popis: | 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. 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 [251170]; Ministerio de Ciencia e Innovacion through the Ramon y Cajal Fellowship |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|