Nhu-Tai Do, Soohyung Kim, Hyung-Jeong Yang, Gueesang Lee, In Seop Na
{"title":"基于卷积神经网络热图的人脸跟踪","authors":"Nhu-Tai Do, Soohyung Kim, Hyung-Jeong Yang, Gueesang Lee, In Seop Na","doi":"10.1145/3184066.3184081","DOIUrl":null,"url":null,"abstract":"In this paper, we apply a heat-map approach for human face tracking. We utilize the heat-map extracted from the convolutional neural networks (CNN) for face / non-face classification problem. The CNN architecture we build is a shallow network to extract information that is meaningful in locating an object. In addition, we made many CNNs with changes in pool-size of the last layer to obtain a well-defined heat-map. Experiments in the Visual Tracking Object dataset show that the results of the method are very encouraging. This shows the effectiveness of our proposed method.","PeriodicalId":109559,"journal":{"name":"International Conference on Machine Learning and Soft Computing","volume":"19 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2018-02-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"7","resultStr":"{\"title\":\"Face tracking with convolutional neural network heat-map\",\"authors\":\"Nhu-Tai Do, Soohyung Kim, Hyung-Jeong Yang, Gueesang Lee, In Seop Na\",\"doi\":\"10.1145/3184066.3184081\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In this paper, we apply a heat-map approach for human face tracking. We utilize the heat-map extracted from the convolutional neural networks (CNN) for face / non-face classification problem. The CNN architecture we build is a shallow network to extract information that is meaningful in locating an object. In addition, we made many CNNs with changes in pool-size of the last layer to obtain a well-defined heat-map. Experiments in the Visual Tracking Object dataset show that the results of the method are very encouraging. This shows the effectiveness of our proposed method.\",\"PeriodicalId\":109559,\"journal\":{\"name\":\"International Conference on Machine Learning and Soft Computing\",\"volume\":\"19 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2018-02-02\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"7\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"International Conference on Machine Learning and Soft Computing\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1145/3184066.3184081\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Conference on Machine Learning and Soft Computing","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/3184066.3184081","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Face tracking with convolutional neural network heat-map
In this paper, we apply a heat-map approach for human face tracking. We utilize the heat-map extracted from the convolutional neural networks (CNN) for face / non-face classification problem. The CNN architecture we build is a shallow network to extract information that is meaningful in locating an object. In addition, we made many CNNs with changes in pool-size of the last layer to obtain a well-defined heat-map. Experiments in the Visual Tracking Object dataset show that the results of the method are very encouraging. This shows the effectiveness of our proposed method.