MARC record from Internet Archive

LEADER: 01950nam 2200301 a 45 0
001 a201324
008 980806s1993 cau b f000|0 eng d
040 $aCMontNP$cCMontNP
086 0 $aD 208.14/2:NPS-CS-93-007
100 1 $aRowe, Neil C.
245 10 $aInferring depictions in natural-language captions for efficient access to picture data /$cNeil C. Rowe.
260 $aMonterey, Calif. :$bNaval Postgraduate School ;$aSpringfield, Va. :$bAvailable from National Technical Information Service,$c[1993]
300 $a20 p. ;$c28 cm.
500 $aTitle from cover.
500 $a"NPS-CS-93-007."
500 $a"July 1993."
500 $a"Technical report October 1, 1992 to July 1993."
500 $aAD A271 396.
504 $aIncludes bibliographical references (p. 17-18).
520 $aMultimedia data can require significant examination time to find desired features ('content analysis'). An alternative is using natural-language captions to describe the data, and matching captions to English queries. But it is hard to include everything in the caption of a complicated datum, so significant content analysis may still seem required. We discuss linguistic clues in captions, both syntactic and semantic, than can simplify or eliminate content analysis. We introduce the notion of concept depiction and rules for depiction inference. Our approach is implemented in an expert system which demonstrated significant increases in recall in experiments. Caption, Multimedia, Information retrieval, Natural language, Parsing, Reference, Prolog
592 $aaq/aq cc:9116 08/06/98
650 4 $aNATURAL LANGUAGE.
650 4 $aDATA DISPLAYS.
650 4 $aPICTURES.
710 2 $aNaval Postgraduate School (U.S.).$bDept. of Computer Science.
740 01 $aNPS-CS-93-007.
926 $aNPS-LIB$bDIGIPROJ$cD 208.14/2:NPS-CS-93-007$dBOOK$eNEVER$f1
926 $aNPS-LIB$bFEDDOCS$cD 208.14/2:NPS-CS-93-007$dBOOK$f2