Abstract | ||
---|---|---|
Existing human action recognition systems for 3D sequences obtained from the depth camera are designed to cope with only one action category, either single-person action or two-person interaction, and are difficult to be extended to scenarios where both action categories co-exist. In this paper, we propose the category-blind human recognition method (CHARM) which can recognize a human action without making assumptions of the action category. In our CHARM approach, we represent a human action (either a single-person action or a two-person interaction) class using a co-occurrence of motion primitives. Subsequently, we classify an action instance based on matching its motion primitive co-occurrence patterns to each class representation. The matching task is formulated as maximum clique problems. We conduct extensive evaluations of CHARM using three datasets for single-person actions, two-person interactions, and their mixtures. Experimental results show that CHARM performs favorably when compared with several state-of-the-art single-person action and two-person interaction based methods without making explicit assumptions of action category. |
Year | DOI | Venue |
---|---|---|
2015 | 10.1109/ICCV.2015.505 | ICCV |
Field | DocType | Volume |
Computer vision,Pattern recognition,Recognition system,Clique,Computer science,Action recognition,Artificial intelligence,Machine learning | Conference | 2015 |
Issue | ISSN | Citations |
1 | 1550-5499 | 12 |
PageRank | References | Authors |
0.59 | 20 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Wenbo Li | 1 | 112 | 9.31 |
Longyin Wen | 2 | 647 | 33.89 |
Mooi Choo Chuah | 3 | 580 | 56.11 |
Siwei Lyu | 4 | 1406 | 135.38 |