Semantic Pyramids for Gender and Action Recognition
- 18 June 2014
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 23 (8) , 3633-3645
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.Keywords
Funding Information
- Swedish Foundation for Strategic Research through the Collaborative Unmanned Aircraft Systems
- 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
This publication has 54 references indexed in Scilit:
- Scale Coding Bag-of-Words for Action Recognition2014
- Head-shoulder based gender recognition2013
- Pixel-Level Hand Detection in Ego-centric Videos2013
- Coloring Action Recognition in Still ImagesInternational Journal of Computer Vision, 2013
- Evaluating the Impact of Color on Texture RecognitionLecture Notes in Computer Science, 2013
- Weakly Supervised Learning of Interactions between Humans and ObjectsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2011
- Action recognition from a distributed representation of pose and appearance2011
- Hand detection using multiple proposals2011
- Evaluation of Gender Classification Methods with Automatically Detected and Aligned FacesIEEE Transactions on Pattern Analysis and Machine Intelligence, 2008
- Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories2006