Abstract
This paper presents an algorithm based on the ideas of bag of words and sparse representation for action recognition. We assume that all action instances form an action space and all action instances from one action class form a subspace of it. Furthermore, the action space can be represented by an over complete basis and each action instance can be represented by a linear combination of the basis. Naturally, the representation is sparse, so we can solve the problem via l1-minimization. Then the action instance is recognized by how well the basis of one class represents it. Our algorithm is tested on the largest action dataset: KHT dataset. The result shows that our algorithm can work well within a relative small train set.
| Original language | English |
|---|---|
| Title of host publication | Proceedings - 2010 3rd International Congress on Image and Signal Processing, CISP 2010 |
| Pages | 372-376 |
| Number of pages | 5 |
| DOIs | |
| Publication status | Published - 2010 |
| Event | 2010 3rd International Congress on Image and Signal Processing, CISP 2010 - Yantai, China Duration: 16 Oct 2010 → 18 Oct 2010 |
Publication series
| Name | Proceedings - 2010 3rd International Congress on Image and Signal Processing, CISP 2010 |
|---|---|
| Volume | 1 |
Conference
| Conference | 2010 3rd International Congress on Image and Signal Processing, CISP 2010 |
|---|---|
| Country/Territory | China |
| City | Yantai |
| Period | 16/10/10 → 18/10/10 |
Fingerprint
Dive into the research topics of 'Sparse representation for action recognition'. Together they form a unique fingerprint.Cite this
Zhang, J., Wang, Y., Chen, J., & Li, Q. (2010). Sparse representation for action recognition. In Proceedings - 2010 3rd International Congress on Image and Signal Processing, CISP 2010 (pp. 372-376). Article 5648024 (Proceedings - 2010 3rd International Congress on Image and Signal Processing, CISP 2010; Vol. 1). https://doi.org/10.1109/CISP.2010.5648024