Matches in SemOpenAlex for { <https://semopenalex.org/work/W2032083927> ?p ?o ?g. }
Showing items 1 to 93 of
93
with 100 items per page.
- W2032083927 abstract "The human face is one of the most important objects in videos since it provides rich information for spotting certain people of interest, such as government leaders in news video, or the hero in a movie, and is the basis for interpreting facts. Therefore, detecting and recognizing faces appearing in video are essential tasks of many video indexing and retrieval applications. Due to large variations in pose changes, illumination conditions, occlusions, hairstyles, and facial expressions, robust face matching has been a challenging problem. In addition, when the number of faces in the dataset is huge, e.g. tens of millions of faces, a scalable method for matching is needed. To this end, we propose an efficient method for face retrieval in large video datasets. In order to make the face retrieval robust, the faces of the same person appearing in individual shots are grouped into a single face track by using a reliable tracking method. The retrieval is done by computing the similarity between face tracks in the databases and the input face track. For each face track, we select one representative face and the similarity between two face tracks is the similarity between their two representative faces. The representative face is the mean face of a subset selected from the original face track. In this way, we can achieve high accuracy in retrieval while maintaining low computational cost. For experiments, we extracted approximately 20 million faces from 370 hours of TRECVID video, of which scale has never been addressed by the former attempts. The results evaluated on a subset consisting of manually annotated 457,320 faces show that the proposed method is effective and scalable." @default.
- W2032083927 created "2016-06-24" @default.
- W2032083927 creator A5006166354 @default.
- W2032083927 creator A5035091959 @default.
- W2032083927 creator A5043063578 @default.
- W2032083927 creator A5057761132 @default.
- W2032083927 creator A5078878666 @default.
- W2032083927 creator A5081841048 @default.
- W2032083927 date "2010-07-05" @default.
- W2032083927 modified "2023-10-16" @default.
- W2032083927 title "An efficient method for face retrieval from large video datasets" @default.
- W2032083927 cites W1537451167 @default.
- W2032083927 cites W1969228515 @default.
- W2032083927 cites W2062903088 @default.
- W2032083927 cites W2121027212 @default.
- W2032083927 cites W2137084491 @default.
- W2032083927 cites W2147717514 @default.
- W2032083927 cites W2163352848 @default.
- W2032083927 cites W2164598857 @default.
- W2032083927 cites W2165307239 @default.
- W2032083927 cites W2171604800 @default.
- W2032083927 doi "https://doi.org/10.1145/1816041.1816096" @default.
- W2032083927 hasPublicationYear "2010" @default.
- W2032083927 type Work @default.
- W2032083927 sameAs 2032083927 @default.
- W2032083927 citedByCount "14" @default.
- W2032083927 countsByYear W20320839272012 @default.
- W2032083927 countsByYear W20320839272013 @default.
- W2032083927 countsByYear W20320839272015 @default.
- W2032083927 countsByYear W20320839272017 @default.
- W2032083927 countsByYear W20320839272018 @default.
- W2032083927 crossrefType "proceedings-article" @default.
- W2032083927 hasAuthorship W2032083927A5006166354 @default.
- W2032083927 hasAuthorship W2032083927A5035091959 @default.
- W2032083927 hasAuthorship W2032083927A5043063578 @default.
- W2032083927 hasAuthorship W2032083927A5057761132 @default.
- W2032083927 hasAuthorship W2032083927A5078878666 @default.
- W2032083927 hasAuthorship W2032083927A5081841048 @default.
- W2032083927 hasConcept C103278499 @default.
- W2032083927 hasConcept C105795698 @default.
- W2032083927 hasConcept C115961682 @default.
- W2032083927 hasConcept C144024400 @default.
- W2032083927 hasConcept C153180895 @default.
- W2032083927 hasConcept C154945302 @default.
- W2032083927 hasConcept C165064840 @default.
- W2032083927 hasConcept C202474056 @default.
- W2032083927 hasConcept C23123220 @default.
- W2032083927 hasConcept C2779304628 @default.
- W2032083927 hasConcept C31510193 @default.
- W2032083927 hasConcept C31972630 @default.
- W2032083927 hasConcept C33923547 @default.
- W2032083927 hasConcept C36289849 @default.
- W2032083927 hasConcept C41008148 @default.
- W2032083927 hasConcept C4641261 @default.
- W2032083927 hasConcept C65483669 @default.
- W2032083927 hasConcept C71681937 @default.
- W2032083927 hasConcept C75165309 @default.
- W2032083927 hasConceptScore W2032083927C103278499 @default.
- W2032083927 hasConceptScore W2032083927C105795698 @default.
- W2032083927 hasConceptScore W2032083927C115961682 @default.
- W2032083927 hasConceptScore W2032083927C144024400 @default.
- W2032083927 hasConceptScore W2032083927C153180895 @default.
- W2032083927 hasConceptScore W2032083927C154945302 @default.
- W2032083927 hasConceptScore W2032083927C165064840 @default.
- W2032083927 hasConceptScore W2032083927C202474056 @default.
- W2032083927 hasConceptScore W2032083927C23123220 @default.
- W2032083927 hasConceptScore W2032083927C2779304628 @default.
- W2032083927 hasConceptScore W2032083927C31510193 @default.
- W2032083927 hasConceptScore W2032083927C31972630 @default.
- W2032083927 hasConceptScore W2032083927C33923547 @default.
- W2032083927 hasConceptScore W2032083927C36289849 @default.
- W2032083927 hasConceptScore W2032083927C41008148 @default.
- W2032083927 hasConceptScore W2032083927C4641261 @default.
- W2032083927 hasConceptScore W2032083927C65483669 @default.
- W2032083927 hasConceptScore W2032083927C71681937 @default.
- W2032083927 hasConceptScore W2032083927C75165309 @default.
- W2032083927 hasLocation W20320839271 @default.
- W2032083927 hasOpenAccess W2032083927 @default.
- W2032083927 hasPrimaryLocation W20320839271 @default.
- W2032083927 hasRelatedWork W1560697087 @default.
- W2032083927 hasRelatedWork W1989039360 @default.
- W2032083927 hasRelatedWork W2003685048 @default.
- W2032083927 hasRelatedWork W2101773345 @default.
- W2032083927 hasRelatedWork W2136321227 @default.
- W2032083927 hasRelatedWork W2532573070 @default.
- W2032083927 hasRelatedWork W2607108626 @default.
- W2032083927 hasRelatedWork W269042006 @default.
- W2032083927 hasRelatedWork W2884888700 @default.
- W2032083927 hasRelatedWork W2997597094 @default.
- W2032083927 isParatext "false" @default.
- W2032083927 isRetracted "false" @default.
- W2032083927 magId "2032083927" @default.
- W2032083927 workType "article" @default.