.png){kind=icon}
返回
Multimodal Face-Pose Estimation With Multitask Manifold Deep Learning
.png){kind=icon}
OA
AI
DOI：10.1109/TII.2018.2884211.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Face-pose estimation aims at estimating the gazing direction with two-dimensional face images. It gives important communicative information and visual saliency. However, it is challenging because of lights, background, face orientations, and appearance visibility. Therefore, a descriptive representation of face images and mapping it to poses are critical. In this paper, we use multimodal data and propose a novel face-pose estimation framework named multitask manifold deep learning ((MDL)-D-2). It is based on feature extractionwith improved convolutional neural networks (CNNs) and multimodal mapping relationship with multitask learning. In the proposed CNNs, manifold regularized convolutional layers learn the relationship between outputs of neurons in a low-rank space. Besides, in the proposed mapping relationship learning method, different modals of face representations are naturally combined by applying multitask learning with incoherent sparse and low-rank learning with a least-squares loss. Experimental results on three challenging benchmark datasets demonstrate the performance of (MDL)-D-2.
Keyword:
Convolutional neural networks (CNNs)
face-pose estimation
low-rank learning
multitask learning
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
9.9
论文数:
8.6K
被引数:
6.0W
机构
引用论文
Funnel-structured cascade for multi-view face detection with alignment awareness.png)
NEUROCOMPUTINGOAAI
NEUROCOMPUTINGIF6.5
OAAI分享收藏Gaze Estimation From Eye Appearance: A Head Pose-Free Method via Eye Image Synthesis从眼睛外观估计注视: 通过眼睛图像合成的无头部姿势方法
PREAI
分享收藏
查看更多内容