Name
Abstract | ||
|---|---|---|
This paper addresses the problem of recognizing human interactions from videos. We propose a novel approach that recognizes human interactions by the learned high-level descriptions, interactive phrases. Interactive phrases describe motion relationships between interacting people. These phrases naturally exploit human knowledge and allow us to construct a more descriptive model for recognizing human interactions. We propose a discriminative model to encode interactive phrases based on the latent SVM formulation. Interactive phrases are treated as latent variables and are used as mid-level features. To complement manually specified interactive phrases, we also discover data-driven phrases from data in order to find potentially useful and discriminative phrases for differentiating human interactions. An information-theoretic approach is employed to learn the data-driven phrases. The interdependencies between interactive phrases are explicitly captured in the model to deal with motion ambiguity and partial occlusion in the interactions. We evaluate our method on the BIT-Interaction data set, UT-Interaction data set, and Collective Activity data set. Experimental results show that our approach achieves superior performance over previous approaches. |
Year | DOI | Venue |
|---|---|---|
2014 | 10.1109/TPAMI.2014.2303090 | IEEE Trans. Pattern Anal. Mach. Intell. |
Keywords | Field | DocType |
mid-level features,video signal processing,collective activity data set,discriminative phrases,human interaction,data-driven phrases,interacting people,latent svm formulation,ut-interaction data set,information-theoretic approach,latent structural svm,descriptive model,interactive phrase encoding,human knowledge,motion relationships,human interaction recognition,action recognition,bit-interaction data set,motion ambiguity,gesture recognition,specified interactive phrases,training video,partial occlusion,learned high-level descriptions,support vector machines,latent variables,semantics,feature extraction,torso,hidden markov models,vectors | Computer vision,ENCODE,Pattern recognition,Computer science,Support vector machine,Latent variable,Feature extraction,Artificial intelligence,Hidden Markov model,Ambiguity,Discriminative model,Semantics | Journal |
Volume | Issue | ISSN |
36 | 9 | 0162-8828 |
Citations | PageRank | References |
46 | 0.96 | 41 |
Authors | ||
3 | ||