Metric Learning from Poses for Temporal Clustering of Human Motion
نویسندگان
چکیده
Segmenting human motion into distinct actions is a highly challenging problem. From the motion analysis perspective, segmentation is difficult due to large stylistic variations, temporal scaling, changes in physical appearance, irregularity in the periodicity of human motions and the huge number of actions and their combinations. From a semantic viewpoint, segmentation is inherently elusive and difficult because in the vast majority of cases it is not clear when a set of poses describes an action. For instance, punching with the left hand and punching with right hand can be different actions, but it might be also regarded as punching or even more general as boxing. We propose to learn what makes a sequence of poses different from others such that it should be annotated as an action, as illustrated in Fig. 1.
منابع مشابه
Composite Kernel Optimization in Semi-Supervised Metric
Machine-learning solutions to classification, clustering and matching problems critically depend on the adopted metric, which in the past was selected heuristically. In the last decade, it has been demonstrated that an appropriate metric can be learnt from data, resulting in superior performance as compared with traditional metrics. This has recently stimulated a considerable interest in the to...
متن کاملHuman Motion Synthesis by Motion Manifold Learning and Motion Primitive Segmentation
We propose motion manifold learning and motion primitive segmentation framework for human motion synthesis from motion-captured data. High dimensional motion capture date are represented using a low dimensional representation by topology preserving network, which maps similar motion instances to the neighborhood points on the low dimensional motion manifold. Nonlinear manifold learning between ...
متن کاملUnsupervised Temporal Segmentation of Human Activities in Video
Human motion analysis from video has attracted much interest from computer vision researchers due to its promising applications for visual surveillance, perceptual user interface, content-based image storage and retrieval, video conferencing, athletic performance analysis and virtual reality. A key aspect to understand and build computational models of human actions is the capability to tempora...
متن کاملیادگیری نیمه نظارتی کرنل مرکب با استفاده از تکنیکهای یادگیری معیار فاصله
Distance metric has a key role in many machine learning and computer vision algorithms so that choosing an appropriate distance metric has a direct effect on the performance of such algorithms. Recently, distance metric learning using labeled data or other available supervisory information has become a very active research area in machine learning applications. Studies in this area have shown t...
متن کاملAn Effective Approach for Robust Metric Learning in the Presence of Label Noise
Many algorithms in machine learning, pattern recognition, and data mining are based on a similarity/distance measure. For example, the kNN classifier and clustering algorithms such as k-means require a similarity/distance function. Also, in Content-Based Information Retrieval (CBIR) systems, we need to rank the retrieved objects based on the similarity to the query. As generic measures such as ...
متن کامل