.png){kind=icon}
返回
Class-balanced siamese neural networks
.png){kind=icon}
OA
AI
DOI：10.1016/j.neucom.2017.07.060.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
This paper focuses on metric learning with Siamese Neural Networks (SNN). Without any prior, SNNs learn to compute a non-linear metric using only similarity and dissimilarity relationships between input data. Our SNN model proposes three contributions: a tuple-based architecture, an objective function with a norm regularisation and a polar sine-based angular reformulation for cosine dissimilarity learning. Applying our SNN model for Human Action Recognition (HAR) gives very competitive results using only one accelerometer or one motion capture point on the Multimodal Human Action Dataset (MHAD). Performances and properties of our proposals in terms of accuracy, convergence and complexity are assessed, with very favourable results. Additional experiments on the Challenge for Multimodal Mid-Air Gesture Recognition for Close Human Computer Interaction Dataset(ChAirGest) confirm the competitive comparison of our proposals with state-of-the-arts models. (C) 2017 Elsevier B.V. All rights reserved.
Keyword:
Siamese neural networks
Metric learning
Human action recognition
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:
6.5
论文数:
2.5W
被引数:
6.5W
机构
引用论文
Transarterial chemoembolization of hepatocellular carcinoma via extrahepatic collateral artery from a supraduodenal and cystic artery trunk, originating from the gastroduodenal artery: A case report经源自胃十二指肠动脉的十二指以上和胆囊动脉干的外生性交通动脉进行的肝细胞癌动脉化疗栓塞术：一例报道OAAI
OAAI分享收藏3D human action recognition model based on image set and regularized multi-task leaning.png)
NEUROCOMPUTING
NEUROCOMPUTINGIF6.5
PREAI
分享收藏Region-based Mixture Models for human action recognition in low-resolution videosNEUROCOMPUTING
NEUROCOMPUTINGIF6.5
PREAI
分享收藏 没有更多内容
没有更多内容