Multi-task Sparse Learning with Beta Process Prior for Action Recognition

Yuan, Chunfeng; Hu, Weiming; Tian, Guodong; Yang, Shuang; Wang, Haoran

doi:10.1109/cvpr.2013.61

Cited by 37 publications

(11 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…MTSL approach combined multiple features efficiently to improve the recognition performance. Its robust sparse coding technique [89]. Details of the parameters can be found in the paper mines correlations between different tasks to obtain a shared sparsity pattern which is ignored if each task is learned individually.…”

Section: Multi-task Sparse Learningmentioning

confidence: 99%

See 1 more Smart Citation

Action Recognition in Realistic Sports Videos

Soomro

Zamir

2014

Advances in Computer Vision and Pattern Recognition

277

183

View full text Add to dashboard Cite

The ability to analyze the actions which occur in a video is essential for automatic understanding of sports. Action localization and recognition in videos are two main research topics in this context. In this chapter, we provide a detailed study of the prominent methods devised for these two tasks which yield superior results for sports videos. We adopt UCF Sports, which is a dataset of realistic sports videos collected from broadcast television channels, as our evaluation benchmark. First, we present an overview of UCF Sports along with comprehensive statistics of the techniques tested on this dataset as well as the evolution of their performance over time. To provide further details about the existing action recognition methods in this area, we decompose the action recognition framework into three main steps of feature extraction, dictionary learning to represent a video, and classification; we overview several successful techniques for each of these steps. We also overview the problem of spatio-temporal localization of actions and argue that, in general, it manifests a more challenging problem compared to action recognition. We study several recent methods for action localization which have shown promising results on sports videos. Finally, we discuss a number of forward-thinking insights drawn from overviewing the action recognition and localization methods. In particular, we argue that performing the recognition on temporally untrimmed videos and attempting to describe an action, instead of conducting a forced-choice classification, are essential for analyzing the human actions in a realistic environment.

show abstract

Section: Multi-task Sparse Learningmentioning

confidence: 99%

“…Multi-Task Sparse Learning (MTSL) [89] aims to construct a given test sample with multiple features and very few bases. In this framework, each feature modality is considered as a single task in MTSL to learn a sparse representation.…”

Section: Multi-task Sparse Learningmentioning

confidence: 99%

Action Recognition in Realistic Sports Videos

Soomro

Zamir

2014

Advances in Computer Vision and Pattern Recognition

277

183

View full text Add to dashboard Cite

show abstract

“…To model complex task dependencies several clustered multi-task learning methods have been introduced [31]- [33]. In computer vision, MTL have been previously proposed in the context of visual-based activity recognition from fixed cameras and in a supervised setting [12], [13], [34]. In this paper, we consider the more challenging FPV scenario where no annotated data are provided.…”

Section: B Supervised Multi-task Learningmentioning

confidence: 99%

Egocentric Daily Activity Recognition via Multitask Clustering

Yan

Ricci

Liu

et al. 2015

IEEE Trans. on Image Process.

139

View full text Add to dashboard Cite

Recognizing human activities from videos is a fundamental research problem in computer vision. Recently, there has been a growing interest in analyzing human behavior from data collected with wearable cameras. First-person cameras continuously record several hours of their wearers' life. To cope with this vast amount of unlabeled and heterogeneous data, novel algorithmic solutions are required. In this paper, we propose a multitask clustering framework for activity of daily living analysis from visual data gathered from wearable cameras. Our intuition is that, even if the data are not annotated, it is possible to exploit the fact that the tasks of recognizing everyday activities of multiple individuals are related, since typically people perform the same actions in similar environments, e.g., people working in an office often read and write documents). In our framework, rather than clustering data from different users separately, we propose to look for clustering partitions which are coherent among related tasks. In particular, two novel multitask clustering algorithms, derived from a common optimization problem, are introduced. Our experimental evaluation, conducted both on synthetic data and on publicly available first-person vision data sets, shows that the proposed approach outperforms several single-task and multitask learning methods.

show abstract

“…Application scenarios include content-based video retrieval, intelligent video surveillance, and human-computer interaction. Although many researchers have done a long-term study in this work, it remains challenging to recognize human actions in videos not only because of geometric variations between intra-class objects or actions, but also because of changes in scale, rotation, viewpoint, illumination, and occlusion [1].…”

Section: Introductionmentioning

confidence: 99%

Spatio-temporal information for human action recognition

Yao

Liu

Huang

2016

J Image Video Proc.

View full text Add to dashboard Cite

Human activity recognition in videos is important for content-based videos indexing, intelligent monitoring, human-machine interaction, and virtual reality. This paper uses the low-level feature-based framework for human activity recognition which includes feature extraction and descriptor computing, early multi-feature fusion, video representation, and classification. This paper improves the first two steps. We propose a spatio-temporal bigraph-based multi-feature fusion algorithm to capture the useful visual information for recognition. Meanwhile, we introduce a compressed spatio-temporal video representation to bag of words representation. Our experiments on two popular datasets show efficient performance.

show abstract

Multi-task Sparse Learning with Beta Process Prior for Action Recognition

Abstract: In this paper, we formulate human action recognition as a novel Multi-Task Sparse Learning(MTSL)

Cited by 37 publications

References 23 publications

Action Recognition in Realistic Sports Videos

Action Recognition in Realistic Sports Videos

Egocentric Daily Activity Recognition via Multitask Clustering

Spatio-temporal information for human action recognition

Contact Info

Product

Resources

About