.png){kind=icon}
返回
Deep CNN based binary hash video representations for face retrieval
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patcog.2018.04.014.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
In this paper, a novel deep convolutional neural network is proposed to learn discriminative binary hash video representations for face retrieval. The network integrates face feature extractor and hash functions into a unified optimization framework to make the two components be as compatible as possible. In order to achieve better initializations for the optimization, the low-rank discriminative binary hashing method is introduced to pre-learn the hash functions of the network during the training procedure. The input to the network is a face frame, and the output is the corresponding binary hash frame representation. Frame representations of a face video shot are fused by hard voting to generate the binary hash video representation. Each bit in the binary representation of frame/video describes the presence or absence of a face attribute, which makes it possible to retrieve faces among both the image and video domains. Extensive experiments are conducted on two challenging TV-Series datasets, and the excellent performance demonstrates the effectiveness of the proposed network. (C) 2018 Elsevier Ltd. All rights reserved.
Keyword:
Face video retrieval
Cross-domain face retrieval
Deep CNN
Hash 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:
7.6
论文数:
1.3W
被引数:
4.5W
机构
引用论文
.png){kind=icon}
分享收藏In-situ IR Spectroscopy to Study Anodic Oxidation of Si(111) in KOH Solution原位红外光谱研究Si(111) 在KOH溶液中的阳极氧化
OAAI
OAAI分享收藏 没有更多内容
没有更多内容