Abstract | ||
---|---|---|
Human interactions and their action categories preserve strong correlations, and the identification of the interaction configuration is of significant importance to improve the action recognition result. However, interactions are typically estimated using heuristics or treated as latent variables. The former usually produces incorrect interaction configuration while the latter introduces challenging training problem. Hence we propose a framework to jointly learn interactions and actions by designing a potential function using both features learned via deep neural networks and human interaction context. We propose an iterative approach to solve the associated inference problem efficiently and approximately. Experimental results on real datasets demonstrate that the proposed approach outperforms baselines by a large margin, and is competitive compared with the state-of-the-arts. |
Year | Venue | Keywords |
---|---|---|
2017 | 2017 24TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP) | Structured prediction, conditional random field, human action recognition, human interaction |
Field | DocType | ISSN |
Pattern recognition,Inference,Computer science,Support vector machine,Action recognition,Baseline (configuration management),Feature extraction,Human interaction,Latent variable,Heuristics,Artificial intelligence,Machine learning | Conference | 1522-4880 |
Citations | PageRank | References |
1 | 0.35 | 0 |
Authors | ||
6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jiali Jin | 1 | 1 | 0.35 |
Zhenhua Wang | 2 | 12 | 3.23 |
Sheng Liu | 3 | 5 | 8.58 |
Jianhua Zhang | 4 | 25 | 5.97 |
Sheng-Yong Chen | 5 | 1077 | 114.06 |
Qiu Guan | 6 | 8 | 3.49 |