End-to-end learning of deformable mixture of parts and deep convolutional neural networks for human pose estimation
Refereed conference paper presented and published in conference proceedings


全文

其它資訊
摘要Recently, Deep Convolutional Neural Networks (DC-NNs) have been applied to the task of human pose estimation, and have shown its potential of learning better feature representations and capturing contextual relationships. However, it is difficult to incorporate domain prior knowledge such as geometric relationships among body parts into DCNNs. In addition, training DCNN-based body part detectors without consideration of global body joint consistency introduces ambiguities, which increases the complexity of training. In this paper, we propose a novel end-to-end framework for human pose estimation that combines DC-NNs with the expressive deformable mixture of parts. We explicitly incorporate domain prior knowledge into the framework, which greatly regularizes the learning process and enables the flexibility of our framework for loopy models or tree-structured models. The effectiveness of jointly learning a DCNN with a deformable mixture of parts model is evaluated through intensive experiments on several widely used benchmarks. The proposed approach significantly improves the performance compared with state-of-the-art approaches, especially on benchmarks with challenging articulations.
著者Yang W., Ouyang W., Li H., Wang X.
會議名稱2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016
會議開始日26.06.2016
會議完結日01.07.2016
會議地點Las Vegas
會議國家/地區美國
出版年份2016
月份1
日期1
卷號2016-January
頁次3073 - 3082
國際標準書號9781467388511
國際標準期刊號1063-6919
語言英式英語

上次更新時間 2020-02-09 於 01:25