{"title":"使基于骨骼的动作识别模型更小、更快、更好","authors":"Fan Yang, S. Sakti, Yang Wu, Satoshi Nakamura","doi":"10.1145/3338533.3366569","DOIUrl":null,"url":null,"abstract":"Although skeleton-based action recognition has achieved great success in recent years, most of the existing methods may suffer from a large model size and slow execution speed. To alleviate this issue, we analyze skeleton sequence properties to propose a Double-feature Double-motion Network (DD-Net) for skeleton-based action recognition. By using a lightweight network structure (i.e., 0.15 million parameters), DD-Net can reach a super fast speed, as 3,500 FPS on an ordinary GPU (e.g., GTX 1080Ti), or, 2,000 FPS on an ordinary CPU (e.g., Intel E5-2620). By employing robust features, DD-Net achieves state-of-the-art performance on our experiment datasets: SHREC (i.e., hand actions) and JHMDB (i.e., body actions). Our code is on https://github.com/fandulu/DD-Net.","PeriodicalId":273086,"journal":{"name":"Proceedings of the ACM Multimedia Asia","volume":"28 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2019-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"103","resultStr":"{\"title\":\"Make Skeleton-based Action Recognition Model Smaller, Faster and Better\",\"authors\":\"Fan Yang, S. Sakti, Yang Wu, Satoshi Nakamura\",\"doi\":\"10.1145/3338533.3366569\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Although skeleton-based action recognition has achieved great success in recent years, most of the existing methods may suffer from a large model size and slow execution speed. To alleviate this issue, we analyze skeleton sequence properties to propose a Double-feature Double-motion Network (DD-Net) for skeleton-based action recognition. By using a lightweight network structure (i.e., 0.15 million parameters), DD-Net can reach a super fast speed, as 3,500 FPS on an ordinary GPU (e.g., GTX 1080Ti), or, 2,000 FPS on an ordinary CPU (e.g., Intel E5-2620). By employing robust features, DD-Net achieves state-of-the-art performance on our experiment datasets: SHREC (i.e., hand actions) and JHMDB (i.e., body actions). Our code is on https://github.com/fandulu/DD-Net.\",\"PeriodicalId\":273086,\"journal\":{\"name\":\"Proceedings of the ACM Multimedia Asia\",\"volume\":\"28 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2019-07-23\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"103\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Proceedings of the ACM Multimedia Asia\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1145/3338533.3366569\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the ACM Multimedia Asia","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/3338533.3366569","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Make Skeleton-based Action Recognition Model Smaller, Faster and Better
Although skeleton-based action recognition has achieved great success in recent years, most of the existing methods may suffer from a large model size and slow execution speed. To alleviate this issue, we analyze skeleton sequence properties to propose a Double-feature Double-motion Network (DD-Net) for skeleton-based action recognition. By using a lightweight network structure (i.e., 0.15 million parameters), DD-Net can reach a super fast speed, as 3,500 FPS on an ordinary GPU (e.g., GTX 1080Ti), or, 2,000 FPS on an ordinary CPU (e.g., Intel E5-2620). By employing robust features, DD-Net achieves state-of-the-art performance on our experiment datasets: SHREC (i.e., hand actions) and JHMDB (i.e., body actions). Our code is on https://github.com/fandulu/DD-Net.