Online multi-task clustering for human motion segmentation
文献类型：会议论文
| 作者 | Sun G(孙干)3,4,5 ; Cong Y(丛杨)3,4; Wang LC(王莅尘)1; DIng ZM(丁正明)2; Fu Y(付昀)1
|
| 出版日期 | 2019 |
| 会议日期 | October 27-28, 2019 |
| 会议地点 | Seoul, Korea, Republic of |
| 页码 | 970-979 |
| 英文摘要 | Human motion segmentation in time space becomes attractive recently due to its wide range of potential applications on action recognition, event detection, and scene understanding tasks. However, most existing state-of-the-arts address this problem upon an offline and single-agent scenario, while there are a lot of urgent requirements to segment videos captured from multiple agents for real-time application (e.g., surveillance system). In this paper, we propose an Online Multi-task Clustering (OMTC) model for an online and multi-agent segmentation scenario, where each agent corresponds to one task. Specifically, a linear autoencoder framework is designed to project motion sequences into a common motion-aware space across multiple collaborating tasks, while the decoder obtains motion-aware representation of each task via a temporal preserved regularizer. To tackle distribution shifts problem between each pair of tasks, the task-specific projections are further proposed to align representation across the motion segmentation tasks. By this way, significant motion knowledge can be shared among multiple tasks, and the temporal data structures are also well preserved. For the model optimization, an efficient and effective online optimization mechanism is derived to solve the large-scale formulation in real-time applications. Experiment results on Keck, MAD and our collected human motion datasets demonstrate the robustness, high-accuracy and efficiency of our OMTC model. |
| 源文献作者 | Computer Vision Foundation ; IEEE |
| 产权排序 | 1 |
| 会议录 | Proceedings - 2019 International Conference on Computer Vision Workshop, ICCVW 2019
 |
| 会议录出版者 | IEEE |
| 会议录出版地 | New York |
| 语种 | 英语 |
| ISBN号 | 978-1-7281-5023-9 |
| WOS记录号 | WOS:000554591601008 |
| 源URL | [http://ir.sia.cn/handle/173321/26625]  |
| 专题 | 沈阳自动化研究所_机器人学研究室 |
| 通讯作者 | Cong Y(丛杨) |
| 作者单位 | 1.Northeastern University, United States 2.Indiana UniversityPurdue University, Indianapolis, United States 3.State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, China 4.Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang, China 5.University of Chinese Academy of Sciences, Beijing 100049, China |
| 推荐引用方式 GB/T 7714 | Sun G,Cong Y,Wang LC,et al. Online multi-task clustering for human motion segmentation[C]. 见:. Seoul, Korea, Republic of. October 27-28, 2019. |
入库方式： OAI收割
来源：沈阳自动化研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。