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

By Chunfen Yuan, Weiming Hu, Guodong Tian, Shuang Yang, Haoran Wang. 2013

49 citations recorded by the source corpus.

In this paper, we formulate human action recognition as a novel Multi-Task Sparse Learning(MTSL) framework which aims to construct a test sample with multiple features from as few bases as possible. Learning the sparse representation under each feature modality is considered as a single task in MTSL. Since the tasks are generated from multiple features associated with the same visual input, they are not independent but inter-related. We introduce a Beta process(BP) prior to the hierarchical MTSL model, which efficiently learns a compact dictionary and infers the sparse structure shared across all the tasks. The MTSL model enforces the robustness in coefficient estimation compared with performing each task independently. Besides, the sparseness is achieved via the Beta process formulation rather than the computationally expensive L1 norm penalty. In terms of non-informative gamma hyper-priors, the sparsity level is totally decided by the data. Finally, the learning problem is solved by Gibbs sampling inference which estimates the full posterior on the model parameters. Experimental results on the KTH and UCF sports datasets demonstrate the effectiveness of the proposed MTSL approach for action recognition.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Representation & Self-Supervised Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Qiang Yang
2. Yu Zhang
3. Mohan Kankanhalli
4. Anan Liu
5. Wei-zhi Nie
6. Yuting Su
7. Mingsheng Long
8. Jianmin Wang

In Computer Vision and Pattern Recognition

1. Qiang Yang
2. Yu Zhang
3. Anan Liu
4. Wei-zhi Nie
5. Mohan Kankanhalli
6. Yuting Su
7. Gabriella Csurka
8. Bernt Schiele

In Representation & Self-Supervised Learning

1. Qiang Yang
2. Yu Zhang
3. Anan Liu
4. Wei-zhi Nie
5. Mohan Kankanhalli
6. Yuting Su
7. Mingsheng Long
8. Jianmin Wang

Citations in the corpus

• An Overview of Multi-task Learning (2018, background): “…images include object categorization [86], image segmentation [89,90], identifying brain imaging predictors [91], saliency detection [92], action recognition [93], scene classification [94], multi-attribute prediction [95], multi-camera person re-identification [96], and immediacy prediction [97].”
• A Survey on Multi-Task Learning (2017, neutral): “In [174], a multi-task sparse model based on the Beta process is proposed to learn dictionaries for action recognition.”
• Hierarchical Clustering Multi-Task Learning for Joint Human Action Grouping and Recognition (2017, methodology): “In contrast to the current methods that either consider all tasks as being related [1], [2] or heuristically impose explicit”