期刊
IEEE TRANSACTIONS ON IMAGE PROCESSING
卷 28, 期 2, 页码 1023-1034出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TIP.2018.2870945
关键词
Human motion segmentation; low-rank learning; temporal data clustering
资金
- NSF IIS Award [1651902]
- U.S. Army Research Office Award [W911NF-17-1-0367]
Human motion segmentation has a great potential in real-world applications. Conventional segmentation approaches cluster data with no guidance from prior knowledge, which could easily cause unpredictable segmentation output and decrease the performance. To this end, we seek to improve the human-motion segmentation performance by fully utilizing pre-existing well-labeled source data. Specifically, we design a new transfer subspace clustering method for motion segmentation with a weighted rank constraint. Specifically, our proposed model obtains the representations of both source and target sequences by mitigating their distribution divergence, which allows for more effective knowledge transfer to the target. To guide new representation learning, we designed a novel sequential graph to preserve temporal information residing in both the source and the target. Furthermore, a weighted low-rank constraint is added to enforce the graph regularizer and uncover clustering structures within data. Experiments are evaluated on four human motion databases, which prove the enhanced performance and increased stability of our model compared with state-of-the-art baselines.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据