Matches in SemOpenAlex for { <https://semopenalex.org/work/W1021004080> ?p ?o ?g. }
Showing items 1 to 60 of
60
with 100 items per page.
- W1021004080 endingPage "158" @default.
- W1021004080 startingPage "147" @default.
- W1021004080 abstract "SIN parses structured activity sequence (or time series data in general).SIN is not a time sliced graphical model.SIN is equivalent to a left-right segmental model (HSMM) and allows exact inference. We propose a new graphical model, called a Sequential Interval Network (SIN), for parsing complex, structured activities whose composition can be represented by a stochastic grammar. By exploiting the grammar, the generated network captures an activity's global temporal structure while avoiding a time-sliced manner model. In this network, the hidden variables are the start and end times of the component actions, which allows reasoning about duration and observation on interval/segment level. Exact inference can be achieved and yield the posterior probabilities of the timing variables as well as each frame's component label. Importantly, by using uninformative expected value of future observations, the network can predict the probability distribution of the timing of future component actions. We demonstrate this framework on vision tasks such as recognition and temporally segmentation of action sequence, or parsing and making future prediction online when running in streaming mode while observing an assembly task." @default.
- W1021004080 created "2016-06-24" @default.
- W1021004080 creator A5014205993 @default.
- W1021004080 creator A5091054255 @default.
- W1021004080 date "2016-02-01" @default.
- W1021004080 modified "2023-10-16" @default.
- W1021004080 title "Sequential Interval Network for parsing complex structured activity" @default.
- W1021004080 cites W1893009044 @default.
- W1021004080 cites W2065804258 @default.
- W1021004080 cites W2076618452 @default.
- W1021004080 cites W2144761450 @default.
- W1021004080 cites W2160517719 @default.
- W1021004080 doi "https://doi.org/10.1016/j.cviu.2015.07.006" @default.
- W1021004080 hasPublicationYear "2016" @default.
- W1021004080 type Work @default.
- W1021004080 sameAs 1021004080 @default.
- W1021004080 citedByCount "6" @default.
- W1021004080 countsByYear W10210040802017 @default.
- W1021004080 countsByYear W10210040802019 @default.
- W1021004080 countsByYear W10210040802020 @default.
- W1021004080 countsByYear W10210040802021 @default.
- W1021004080 crossrefType "journal-article" @default.
- W1021004080 hasAuthorship W1021004080A5014205993 @default.
- W1021004080 hasAuthorship W1021004080A5091054255 @default.
- W1021004080 hasConcept C11413529 @default.
- W1021004080 hasConcept C114614502 @default.
- W1021004080 hasConcept C154945302 @default.
- W1021004080 hasConcept C186644900 @default.
- W1021004080 hasConcept C204321447 @default.
- W1021004080 hasConcept C2778067643 @default.
- W1021004080 hasConcept C33923547 @default.
- W1021004080 hasConcept C41008148 @default.
- W1021004080 hasConceptScore W1021004080C11413529 @default.
- W1021004080 hasConceptScore W1021004080C114614502 @default.
- W1021004080 hasConceptScore W1021004080C154945302 @default.
- W1021004080 hasConceptScore W1021004080C186644900 @default.
- W1021004080 hasConceptScore W1021004080C204321447 @default.
- W1021004080 hasConceptScore W1021004080C2778067643 @default.
- W1021004080 hasConceptScore W1021004080C33923547 @default.
- W1021004080 hasConceptScore W1021004080C41008148 @default.
- W1021004080 hasLocation W10210040801 @default.
- W1021004080 hasOpenAccess W1021004080 @default.
- W1021004080 hasPrimaryLocation W10210040801 @default.
- W1021004080 hasRelatedWork W1552159754 @default.
- W1021004080 hasRelatedWork W1592893681 @default.
- W1021004080 hasRelatedWork W180507639 @default.
- W1021004080 hasRelatedWork W1806995473 @default.
- W1021004080 hasRelatedWork W1978971213 @default.
- W1021004080 hasRelatedWork W2138067497 @default.
- W1021004080 hasRelatedWork W2167662847 @default.
- W1021004080 hasRelatedWork W2502722637 @default.
- W1021004080 hasRelatedWork W1551406738 @default.
- W1021004080 hasRelatedWork W2594281132 @default.
- W1021004080 hasVolume "143" @default.
- W1021004080 isParatext "false" @default.
- W1021004080 isRetracted "false" @default.
- W1021004080 magId "1021004080" @default.
- W1021004080 workType "article" @default.