Abstract | ||
---|---|---|
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. |
Year | DOI | Venue |
---|---|---|
2014 | 10.1109/TIP.2014.2331759 | IEEE Transactions on Image Processing |
Keywords | Field | DocType |
occupational safety,injury prevention,suicide prevention,human factors,ergonomics | Computer vision,Data set,Normalization (statistics),Three-dimensional face recognition,Pattern recognition,Proxemics,Feature extraction,Artificial intelligence,Pyramid,Mathematics,Bounding overwatch,Minimum bounding box | Journal |
Volume | Issue | ISSN |
23 | 8 | 1057-7149 |
Citations | PageRank | References |
7 | 0.42 | 35 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Fahad Shahbaz Khan | 1 | 1622 | 69.24 |
Joost van de Weijer | 2 | 2117 | 124.82 |
Muhammad Anwer Rao | 3 | 129 | 11.22 |
Michael Felsberg | 4 | 2419 | 130.29 |
Carlo Gatta | 5 | 7 | 0.42 |