{"title":"A Standalone Demo for Quiz Game \"Describe and Guess\"","authors":"Yikun Sheng, Xiaoshan Yang, Changsheng Xu","doi":"10.1109/MIPR.2018.00046","DOIUrl":null,"url":null,"abstract":"The popular quiz game \"Describe and Guess\" can only be played by at least two players which limits its utilization. In this paper, we propose a standalone demo with a multimodal interface which is much more convenient for a single player. To deduce the target object based on user-provided attributes and sketches, we propose attributeimproved neural networks (AINN) which are joint learned for both the single-label object classification and the multilabel attribute prediction. Finally, we build a real-world system which can be effectively played on mobile devices.","PeriodicalId":320000,"journal":{"name":"2018 IEEE Conference on Multimedia Information Processing and Retrieval (MIPR)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2018-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2018 IEEE Conference on Multimedia Information Processing and Retrieval (MIPR)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/MIPR.2018.00046","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
The popular quiz game "Describe and Guess" can only be played by at least two players which limits its utilization. In this paper, we propose a standalone demo with a multimodal interface which is much more convenient for a single player. To deduce the target object based on user-provided attributes and sketches, we propose attributeimproved neural networks (AINN) which are joint learned for both the single-label object classification and the multilabel attribute prediction. Finally, we build a real-world system which can be effectively played on mobile devices.