Action Status Based Novel Relative Feature Representations for Interaction Recognition

来源 :电子学报(英文版) | 被引量 : 0次 | 上传用户:qiyueliuhua
下载到本地 , 更方便阅读
声明 : 本文档内容版权归属内容提供方 , 如果您对本文有版权争议 , 可与客服联系进行内容授权或下架
论文部分内容阅读
Skeleton-based action recognition has al-ways been an important research topic in computer vis-ion.Most of the researchers in this field currently pay more attention to actions performed by a single person while there is very little work dedicated to the identifica-tion of interactions between two people.However,the practical application of interaction recognition is actually more critical in our society considering that actions are often performed by multiple people.How to design an ef-fective scheme to learn discriminative spatial and tempor-al representations for skeleton-based interaction recogni-tion is still a challenging problem.Focusing on the char-acteristics of skeleton data for interactions,we first define the moving distance to distinguish the action status of the participants.Then some view-invariant relative features are proposed to fully represent the spatial and temporal relationship of the skeleton sequence.Further,a new cod-ing method is proposed to obtain the novel relative fea-ture representations.Finally,we design a three-stream CNN model to learn deep features for interaction recogni-tion.We evaluate our method on SBU dataset,NTU RGB+D 60 dataset and NTU RGB+D 120 dataset.The experimental results also verify that our method is effect-ive and exhibits great robustness compared with current state-of-the-art methods.
其他文献
The conventional convolutional neural network performs not well enough in the ground objects classification because of its insufficient ability in maintain-ing sensitive spectral information and characterizing the covariance of spatial structure,resulting
In this paper,a hybrid deep learning network-based model is proposed and implemented for maneuver decision-making in an air combat environment.The model consists of stacked sparse auto-encoder net-work for dimensionality reduction of high-dimensional,dyna
Unsupervised person re-identification(Re-ID)aims to improve the model\'s scalability and ob-tain better Re-ID results in the unlabeled data domain.In this paper,we propose an unsupervised person Re-ID method based on multi-granularity feature representa
A new classification model,the fuzzy hy-brid twin support vector machine(TWSVM),namely FHTWSVM,is proposed by combining the fuzzy TWS-VM and the hypersphere support vector machine(SVM).The hypersphere SVM is utilized for generating the hy-perspheres for t
2月16日,据世界经济论坛网站发布的WEF智能工业指数认证白皮书《制造业转型洞察报告》显示,海尔洗衣机旗下中德滚筒互联工厂和海尔合肥洗衣机互联工厂入选该报告,成为全球洗衣机行业唯一入选的优秀案例代表,再次证明了海尔洗衣机的智能制造实力.
期刊
Speech emotion recognition(SER)is the use of speech signals to estimate the state of emotion.At present,machine learning is one of the main research methods of SER,the test and training dataS of tradition-al machine learning all have the same distribution
This paper reports a successive approx-imation register(SAR)analog-to-digital converters(ADCs)with the 2nd-order and optimized noise shaping(NS)scheme.Based on the feed-forward structure,both noise transfer function(NTF)zero and pole optimization have bee
With the development of face image syn-thesis and generation technology based on generative ad-versarial networks(GANs),it has become a research hot-spot to determine whether a given face image is natural or generated.However,the generalization capability
垃圾处理器市场体量偏小,但随着政策推动市场,加之疫情催生人们对于健康绿色生活和品质居住的关注以及90后消费群体崛起带来的“懒人经济”,这些都将为厨余垃圾处理器行业带来长期利好.据奥维云网(AVC)线上监测数据,2021年1~12月垃圾处理器行业线上零售量22.2万台,零售额4.9亿.
期刊
The data with both a linear ordering and a hierarchically nested one-to-one matching of items is ubiquitous,including parenthesis matching languages and hypertext markup language/extensive markup language(HTML/XML)documents.There exist some real-world pro