Loading...
Please wait, while we are loading the content...
Similar Documents
Latent Multitask Learning for View-Invariant Action Recognition
| Content Provider | CiteSeerX |
|---|---|
| Author | Mahasseni, Behrooz Todorovic, Sinisa |
| Abstract | This paper presents an approach to view-invariant ac-tion recognition, where human poses and motions exhibit large variations across different camera viewpoints. When each viewpoint of a given set of action classes is specified as a learning task then multitask learning appears suitable for achieving view invariance in recognition. We extend the standard multitask learning to allow identifying: (1) latent groupings of action views (i.e., tasks), and (2) discrimi-native action parts, along with joint learning of all tasks. This is because it seems reasonable to expect that certain distinct views are more correlated than some others, and thus identifying correlated views could improve recognition. Also, part-based modeling is expected to improve robust-ness against self-occlusion when actors are imaged from different views. Results on the benchmark datasets show that we outperform standard multitask learning by 21.9%, and the state-of-the-art alternatives by 4.5–6%. 1. |
| File Format | |
| Access Restriction | Open |
| Subject Keyword | View-invariant Action Recognition Latent Multitask Learning Certain Distinct View Different Camera Viewpoint View-invariant Ac-tion Recognition Action Class Joint Learning Different View Part-based Modeling Action View Large Variation Standard Multitask Learning Human Pose Latent Grouping Discrimi-native Action Part State-of-the-art Alternative Learning Task Standard Multitask View Invariance |
| Content Type | Text |
| Resource Type | Article |
