BARN:Behavior-Aware Relation Network for multi-label behavior detection in socially housed macaques

作     者：Sen Yang Zhi-Yuan Chen Ke-Wei Liang Cai-Jie Qin Yang Yang Wen-Xuan Fan Chen-Lu Jie Xi-Bo Ma Sen Yang;Zhi-Yuan Chen;Ke-Wei Liang;Cai-Jie Qin;Yang Yang;Wen-Xuan Fan;Chen-Lu Jie;Xi-Bo Ma

作者机构：College of Medicine and Biological Information EngineeringNortheastern UniversityShenyangLiaoning 110169China MAISState Key Laboratory of Multimodal Artificial Intelligence SystemsInstitute of AutomationChinese Academy of SciencesBeijing 100190China School of Artificial IntelligenceUniversity of Chinese Academy of SciencesBeijing100049China School of AutomationHarbin University of Science and TechnologyHarbinHeilongjiang 150080China 

出 版 物：《Zoological Research》 (动物学研究（英文）)

年 卷 期：2023年第44卷第6期

页      面：1026-1038页

核心收录：

学科分类：0710[理学-生物学] 07[理学] 071002[理学-动物学] 

基　　金：supported by the Major Project of the National Natural Science Foundation of China (82090051,81871442) Outstanding Member Project of Youth Innovation Promotion Association of the Chinese Academy of Sciences (Y201930) 

主　　题：Macaque behavior Drug safety assessment Multi-label behavior detection Behavioral similarity Relation network 

摘      要：Quantification of behaviors in macaques provides crucial support for various scientific disciplines,including pharmacology,neuroscience,and *** recent advancements in the analysis of macaque behavior,research on multi-label behavior detection in socially housed macaques,including consideration of interactions among them,remains *** the lack of relevant approaches and datasets,we developed the Behavior-Aware Relation Network(BARN)for multi-label behavior detection of socially housed *** approach models the relationship of behavioral similarity between macaques,guided by a behavior-aware module and novel behavior classifier,which is suitable for multi-label *** also constructed a behavior dataset of rhesus macaques using ordinary RGB cameras mounted outside their *** dataset included 65?913 labels for19 behaviors and 60?367 proposals,including identities and locations of the *** results showed that BARN significantly improved the baseline SlowFast network and outperformed existing relation *** conclusion,we successfully achieved multilabel behavior detection of socially housed macaques with both economic efficiency and high accuracy.