Title
Recognizing Human Actions Using Multiple Features
Abstract
In this paper, we propose a framework that fuses multiple features for improved action recognition in videos. The fusion of multiple features is important for recognizing actions as often a single feature based representation is not enough to capture the imaging variations (view-point, illumination etc.) and attributes of individuals (size, age, gender etc.). Hence, we use two types of features: i) a quantized vocabulary of local spatio-temporal (ST) volumes (or cuboids), and ii) a quantized vocabulary of spin-images, which aims to capture the shape deformation of the actor by considering actions as 3D objects (x, y, t). To optimally combine these features, we treat different features as nodes in a graph, where weighted edges between the nodes represent the strength of the relationship between entities. The graph is then embedded into a k-dimensional space subject to the criteria that similar nodes have Euclidian coordinates which are closer to each other. This is achieved by converting this constraint into a minimization problem whose solution is the eigenvectors of the graph Laplacian matrix. This procedure is known as Fiedler Embedding. The performance of the proposed framework is tested on publicly available data sets. The results demonstrate that fusion of multiple features helps in achieving improved performance, and allows retrieval of meaningful features and videos from the embedding space. ©2008 IEEE.
Publication Date
9-23-2008
Publication Title
26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR
Number of Pages
-
Document Type
Article; Proceedings Paper
Personal Identifier
scopus
DOI Link
https://doi.org/10.1109/CVPR.2008.4587527
Copyright Status
Unknown
Socpus ID
51949105885 (Scopus)
Source API URL
https://api.elsevier.com/content/abstract/scopus_id/51949105885
STARS Citation
Liu, Jingen; Ali, Saad; and Shah, Mubarak, "Recognizing Human Actions Using Multiple Features" (2008). Scopus Export 2000s. 10209.
https://stars.library.ucf.edu/scopus2000/10209