Name
Title | ||
|---|---|---|
Modeling temporal interactions with interval temporal bayesian networks for complex activity recognition. |
Abstract | ||
|---|---|---|
Complex activities typically consist of multiple primitive events happening in parallel or sequentially over a period of time. Understanding such activities requires recognizing not only each individual event but, more importantly, capturing their spatiotemporal dependencies over different time intervals. Most of the current graphical model-based approaches have several limitations. First, time--sliced graphical models such as hidden Markov models (HMMs) and dynamic Bayesian networks are typically based on points of time and they hence can only capture three temporal relations: precedes, follows, and equals. Second, HMMs are probabilistic finite-state machines that grow exponentially as the number of parallel events increases. Third, other approaches such as syntactic and description-based methods, while rich in modeling temporal relationships, do not have the expressive power to capture uncertainties. To address these issues, we introduce the interval temporal Bayesian network (ITBN), a novel graphical model that combines the Bayesian Network with the interval algebra to explicitly model the temporal dependencies over time intervals. Advanced machine learning methods are introduced to learn the ITBN model structure and parameters. Experimental results show that by reasoning with spatiotemporal dependencies, the proposed model leads to a significantly improved performance when modeling and recognizing complex activities involving both parallel and sequential events. |
Year | DOI | Venue |
|---|---|---|
2013 | 10.1109/TPAMI.2013.33 | IEEE Trans. Pattern Anal. Mach. Intell. |
Keywords | Field | DocType |
complex activity recognition,interval temporal bayesian networks,different time interval,itbn model structure,interval temporal bayesian network,novel graphical model,spatiotemporal dependency,modeling temporal interactions,complex activity,hidden markov model,sliced graphical model,time interval,hidden markov models,activity recognition,algebra,bayesian networks,learning artificial intelligence,probabilistic logic,dynamic bayesian networks,graphical models,computational modeling,hmm,object recognition,uncertainty,bayesian methods | Activity recognition,Pattern recognition,Computer science,Bayesian network,Artificial intelligence,Graphical model,Probabilistic logic,Hidden Markov model,Machine learning,Cognitive neuroscience of visual object recognition,Dynamic Bayesian network,Bayesian probability | Journal |
Volume | Issue | ISSN |
35 | 10 | 1939-3539 |
Citations | PageRank | References |
29 | 0.92 | 43 |
Authors | ||
6 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Yongmian Zhang | 1 | 381 | 18.78 |
| Yifan Zhang | 2 | 512 | 30.27 |
| Eran Swears | 3 | 255 | 10.48 |
| Natalia Larios | 4 | 63 | 2.66 |
| Ziheng Wang | 5 | 199 | 7.92 |
| Qiang Ji | 6 | 758 | 49.26 |