Multi-View Perceptron: a Deep Model for LearningFace Identity and View Representations | |
Zhenyao Zhu; Ping Luo; Xiaogang Wang; Xiaoou Tang | |
2014 | |
会议名称 | The 28 Annual Conference on Neural Information Processing Systems (NIPS) |
会议地点 | 加拿大 |
英文摘要 | Various factors, such as identity, view, and illumination, are coupled in face images. Disentangling the identity and view representations is a major challenge in face recognition. Existing face recognition systems either use handcrafted features or learn features discriminatively to improve recognition accuracy. This is different from the behavior of primate brain. Recent studies [5, 19] discovered that primate brain has a face-processing network, where view and identity are processed by different neurons. Taking into account this instinct, this paper proposes a novel deep neural net, named multi-view perceptron (MVP), which can untangle the identity and view features, and in the meanwhile infer a full spectrum of multi-view images, given a single 2D face image. The identity features of MVP achieve superior performance on the MultiPIE dataset. MVP is also capable to interpolateandpredictimagesunderviewpointsthatareunobservedinthetraining data. |
收录类别 | 其他 |
语种 | 英语 |
内容类型 | 会议论文 |
源URL | [http://ir.siat.ac.cn:8080/handle/172644/5505] ![]() |
专题 | 深圳先进技术研究院_集成所 |
作者单位 | 2014 |
推荐引用方式 GB/T 7714 | Zhenyao Zhu,Ping Luo,Xiaogang Wang,et al. Multi-View Perceptron: a Deep Model for LearningFace Identity and View Representations[C]. 见:The 28 Annual Conference on Neural Information Processing Systems (NIPS). 加拿大. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论