Matches in SemOpenAlex for { <https://semopenalex.org/work/W2024196246> ?p ?o ?g. }
- W2024196246 endingPage "1100" @default.
- W2024196246 startingPage "1081" @default.
- W2024196246 abstract "We present a trainable sequential-inference technique for processes with large state and observation spaces and relational structure. We apply our technique to the problem of force-dynamic state inference from video, which is a critical component of the LEONARD [J.M. Siskind, Grounding lexical semantics of verbs in visual perception using force dynamics and event logic, Journal of Artificial Intelligence Research 15 (2001) 31–90] visual-event recognition system. LEONARD uses event definitions that are grounded in force-dynamic primitives—making robust and efficient force-dynamic inference critical to good performance. Our sequential-inference method assumes “reliable observations”, i.e., that each process state (e.g., force-dynamic state) persists long enough to be reliably inferred from the observations (e.g., video frames) it generates. We introduce the idea of a “state-inference function” (from observation sequences to underlying hidden states) for representing knowledge about a process and develop an efficient sequential-inference algorithm, utilizing this function, that is correct for processes that generate reliable observations consistent with the state-inference function. We describe a representation for state-inference functions in relational domains and give a corresponding supervised learning algorithm. Our experiments in force-dynamic state inference show that our technique provides significantly improved accuracy and speed relative to a variety of recent, hand-coded, non-trainable systems, and a trainable system based on probabilistic modeling." @default.
- W2024196246 created "2016-06-24" @default.
- W2024196246 creator A5007751369 @default.
- W2024196246 creator A5030052689 @default.
- W2024196246 date "2006-10-01" @default.
- W2024196246 modified "2023-09-25" @default.
- W2024196246 title "Sequential inference with reliable observations: Learning to construct force-dynamic models" @default.
- W2024196246 cites W1529355025 @default.
- W2024196246 cites W1532399371 @default.
- W2024196246 cites W1771552368 @default.
- W2024196246 cites W1791364091 @default.
- W2024196246 cites W1910567995 @default.
- W2024196246 cites W1966522052 @default.
- W2024196246 cites W1966965607 @default.
- W2024196246 cites W1975130368 @default.
- W2024196246 cites W1977970897 @default.
- W2024196246 cites W1982333717 @default.
- W2024196246 cites W1987902506 @default.
- W2024196246 cites W1992810975 @default.
- W2024196246 cites W1999138184 @default.
- W2024196246 cites W2008652694 @default.
- W2024196246 cites W2020294948 @default.
- W2024196246 cites W2028137574 @default.
- W2024196246 cites W202901394 @default.
- W2024196246 cites W2036368940 @default.
- W2024196246 cites W2040870580 @default.
- W2024196246 cites W2047317708 @default.
- W2024196246 cites W2083393647 @default.
- W2024196246 cites W2108308566 @default.
- W2024196246 cites W2112796928 @default.
- W2024196246 cites W2119171928 @default.
- W2024196246 cites W2119232785 @default.
- W2024196246 cites W2124077104 @default.
- W2024196246 cites W2125838338 @default.
- W2024196246 cites W2126185296 @default.
- W2024196246 cites W2128554449 @default.
- W2024196246 cites W2147880316 @default.
- W2024196246 cites W2152239535 @default.
- W2024196246 cites W2153710242 @default.
- W2024196246 cites W2159080219 @default.
- W2024196246 cites W2161290181 @default.
- W2024196246 cites W2162621793 @default.
- W2024196246 cites W2165013021 @default.
- W2024196246 cites W2309703928 @default.
- W2024196246 cites W2914587038 @default.
- W2024196246 cites W2962735828 @default.
- W2024196246 cites W330951725 @default.
- W2024196246 cites W34322314 @default.
- W2024196246 cites W62514041 @default.
- W2024196246 cites W164048988 @default.
- W2024196246 doi "https://doi.org/10.1016/j.artint.2006.08.003" @default.
- W2024196246 hasPublicationYear "2006" @default.
- W2024196246 type Work @default.
- W2024196246 sameAs 2024196246 @default.
- W2024196246 citedByCount "4" @default.
- W2024196246 crossrefType "journal-article" @default.
- W2024196246 hasAuthorship W2024196246A5007751369 @default.
- W2024196246 hasAuthorship W2024196246A5030052689 @default.
- W2024196246 hasConcept C119857082 @default.
- W2024196246 hasConcept C121332964 @default.
- W2024196246 hasConcept C14036430 @default.
- W2024196246 hasConcept C154945302 @default.
- W2024196246 hasConcept C17744445 @default.
- W2024196246 hasConcept C199539241 @default.
- W2024196246 hasConcept C2776214188 @default.
- W2024196246 hasConcept C2776359362 @default.
- W2024196246 hasConcept C2779662365 @default.
- W2024196246 hasConcept C41008148 @default.
- W2024196246 hasConcept C62520636 @default.
- W2024196246 hasConcept C78458016 @default.
- W2024196246 hasConcept C86803240 @default.
- W2024196246 hasConcept C94625758 @default.
- W2024196246 hasConceptScore W2024196246C119857082 @default.
- W2024196246 hasConceptScore W2024196246C121332964 @default.
- W2024196246 hasConceptScore W2024196246C14036430 @default.
- W2024196246 hasConceptScore W2024196246C154945302 @default.
- W2024196246 hasConceptScore W2024196246C17744445 @default.
- W2024196246 hasConceptScore W2024196246C199539241 @default.
- W2024196246 hasConceptScore W2024196246C2776214188 @default.
- W2024196246 hasConceptScore W2024196246C2776359362 @default.
- W2024196246 hasConceptScore W2024196246C2779662365 @default.
- W2024196246 hasConceptScore W2024196246C41008148 @default.
- W2024196246 hasConceptScore W2024196246C62520636 @default.
- W2024196246 hasConceptScore W2024196246C78458016 @default.
- W2024196246 hasConceptScore W2024196246C86803240 @default.
- W2024196246 hasConceptScore W2024196246C94625758 @default.
- W2024196246 hasIssue "14-15" @default.
- W2024196246 hasLocation W20241962461 @default.
- W2024196246 hasOpenAccess W2024196246 @default.
- W2024196246 hasPrimaryLocation W20241962461 @default.
- W2024196246 hasRelatedWork W2511279186 @default.
- W2024196246 hasRelatedWork W2961085424 @default.
- W2024196246 hasRelatedWork W3046775127 @default.
- W2024196246 hasRelatedWork W3107474891 @default.
- W2024196246 hasRelatedWork W3209574120 @default.
- W2024196246 hasRelatedWork W4205958290 @default.
- W2024196246 hasRelatedWork W4286629047 @default.
- W2024196246 hasRelatedWork W4306321456 @default.