Name
Title | ||
|---|---|---|
Leveraging Temporal, Contextual And Ordering Constraints For Recognizing Complex Activities In Video |
Abstract | ||
|---|---|---|
We present a scalable approach to recognizing and describing complex activities in video sequences. We are interested in long-term, sequential activities that may have several parallel streams of action. Our approach integrates temporal, contextual and ordering constraints with output from low-level visual detectors to recognize complex, long-term activities. We argue that a hierarchical, object-oriented design lends our solution to be scalable in that higher-level reasoning components are independent from the particular low-level detector implementation and that recognition of additional activities and actions can easily be added. Three major components to realize this design are: a dynamic Bayesian network structure for representing activities comprised of partially ordered sub-actions, an object-oriented action hierarchy for building arbitrarily complex action detectors and an approximate Viterbi-like algorithm for inferring the most likely observed sequence of actions. Additionally, this study proposes the Erlang distribution as a comprehensive model of idle time between actions and frequency of observing new actions. We show results for our approach on real video sequences containing complex activities. |
Year | DOI | Venue |
|---|---|---|
2007 | 10.1109/CVPR.2007.383074 | 2007 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, VOLS 1-8 |
Keywords | Field | DocType |
erlang distribution,dynamic bayesian network,algorithm design and analysis,object oriented,object oriented design,bayesian methods,partial order,detectors,computer science,viterbi algorithm | Erlang distribution,Object oriented methods,Computer science,Theoretical computer science,Artificial intelligence,Hierarchy,Detector,Machine learning,Idle time,Dynamic Bayesian network,Scalability | Conference |
Volume | Issue | ISSN |
2007 | 1 | 1063-6919 |
Citations | PageRank | References |
74 | 2.72 | 22 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Benjamin Laxton | 1 | 86 | 4.60 |
| Jongwoo Lim | 2 | 4105 | 144.58 |
| David Kriegman | 3 | 7693 | 451.96 |