Humans regularly interact with their surrounding objects.Such interactions often result in strongly correlated motions between humans and the interacting objects.We thus ask:"Is it possible to infer object proper...Humans regularly interact with their surrounding objects.Such interactions often result in strongly correlated motions between humans and the interacting objects.We thus ask:"Is it possible to infer object properties from skeletal motion alone,even without seeing the interacting object itself?"In this paper,we present a fine-grained action recognition method that learns to infer such latent object properties from human interaction motion alone.This inference allows us to disentangle the motion from the object property and transfer object properties to a given motion.We collected a large number of videos and 3 D skeletal motions of performing actors using an inertial motion capture device.We analyzed similar actions and learned subtle differences between them to reveal latent properties of the interacting objects.In particular,we learned to identify the interacting object,by estimating its weight,or its spillability.Our results clearly demonstrate that motions and interacting objects are highly correlated and that related object latent properties can be inferred from 3 D skeleton sequences alone,leading to new synthesis possibilities for motions involving human interaction.Our dataset is available at http://vcc.szu.edu.cn/research/2020/IT.html.展开更多
Language is a symbolic system consisting of the signifier and the signified.There is an asymmetrical binary correspondence between them,which is also widespread in Russian linguistics.There are two main types of inter...Language is a symbolic system consisting of the signifier and the signified.There is an asymmetrical binary correspondence between them,which is also widespread in Russian linguistics.There are two main types of interrogative sentence formed by the interrogative pronounкакой.Traditional lexicography and grammar have limitations in their understanding ofкакойand of the interrogative sentences it forms.The analysis of such syntactic phenomena should be included in the Q–A unity,which can be described in terms of argument structures,generic relations,deixis,relevant characteristics,properties,or attributes of objects,etc.展开更多
基金supported in part by Shenzhen Innovation Program(JCYJ20180305125709986)National Natural Science Foundation of China(61861130365,61761146002)+1 种基金GD Science and Technology Program(2020A0505100064,2015A030312015)DEGP Key Project(2018KZDXM058)。
文摘Humans regularly interact with their surrounding objects.Such interactions often result in strongly correlated motions between humans and the interacting objects.We thus ask:"Is it possible to infer object properties from skeletal motion alone,even without seeing the interacting object itself?"In this paper,we present a fine-grained action recognition method that learns to infer such latent object properties from human interaction motion alone.This inference allows us to disentangle the motion from the object property and transfer object properties to a given motion.We collected a large number of videos and 3 D skeletal motions of performing actors using an inertial motion capture device.We analyzed similar actions and learned subtle differences between them to reveal latent properties of the interacting objects.In particular,we learned to identify the interacting object,by estimating its weight,or its spillability.Our results clearly demonstrate that motions and interacting objects are highly correlated and that related object latent properties can be inferred from 3 D skeleton sequences alone,leading to new synthesis possibilities for motions involving human interaction.Our dataset is available at http://vcc.szu.edu.cn/research/2020/IT.html.
基金This paper is a partial result of the research“On the interaction between Q&A in Russian wh-questions with interrogative pronouns”(No.2020SJA1361)which is sponsored by the Philosophical and Social Science Research Projects in Jiangsu Universities.
文摘Language is a symbolic system consisting of the signifier and the signified.There is an asymmetrical binary correspondence between them,which is also widespread in Russian linguistics.There are two main types of interrogative sentence formed by the interrogative pronounкакой.Traditional lexicography and grammar have limitations in their understanding ofкакойand of the interrogative sentences it forms.The analysis of such syntactic phenomena should be included in the Q–A unity,which can be described in terms of argument structures,generic relations,deixis,relevant characteristics,properties,or attributes of objects,etc.
