One-Sequence Learning of Human Actions.
ABSTRACT In this paper we address the problem of human action recognition from a single training sequence per class using a modified version of the Hidden Markov Model. Inspired by codebook approaches in object and scene categorization, we first construct a codebook of possible discrete observations by applying a clustering algorithm to all samples from all classes. The number of clusters defines the size of the codebook. Given a new observation, we assign to it a probability to belong to every cluster, i.e., to correspond to a discrete value of the codebook. In this sense, we change the ‘winner takes all' rule in the discrete-observation HMM for a distributed probability of membership. It implies the modification of the Baum-Welch algorithm for training discrete HMM to be able to deal with fuzzy observations. We compare our approach with other models such as, dynamic time warping (DTW), continuous-observation HMM, Conditional Random Fields (CRF) and Hidden Conditional Random Fields (HCRF) for human action recognition.
- SourceAvailable from: Albert Ali Salah[Show abstract] [Hide abstract]
ABSTRACT: Pervasive sensing and human behavior understanding can help us in implementing or improving systems that can induce behavioral change. In this introductory paper of the 2nd International Workshop on Human Behavior Understanding (HBU'11), which has a special focus theme of “Inducing Behavioral Change”, we provide a taxonomy to describe where and how HBU technology can be harnessed to this end, and supply a short survey of the area from an application perspective. We also consider how social signals and settings relate to this concept.Human Behavior Unterstanding - Second International Workshop, HBU 2011, Amsterdam, The Netherlands, November 16, 2011. Proceedings; 01/2011
- [Show abstract] [Hide abstract]
ABSTRACT: Regular machine learning and data mining techniques study the training data for future inferences under a major assumption that the future data are within the same feature space or have the same distribution as the training data. However, due to the limited availability of human labeled training data, training data that stay in the same feature space or have the same distribution as the future data cannot be guaranteed to be sufficient enough to avoid the over-fitting problem. In real-world applications, apart from data in the target domain, related data in a different domain can also be included to expand the availability of our prior knowledge about the target future data. Transfer learning addresses such cross-domain learning problems by extracting useful information from data in a related domain and transferring them for being used in target tasks. In recent years, with transfer learning being applied to visual categorization, some typical problems, e.g., view divergence in action recognition tasks and concept drifting in image classification tasks, can be efficiently solved. In this paper, we survey state-of-the-art transfer learning algorithms in visual categorization applications, such as object recognition, image classification, and human action recognition.IEEE transactions on neural networks and learning systems 07/2014; 26(5). DOI:10.1109/TNNLS.2014.2330900 · 4.37 Impact Factor