Matches in SemOpenAlex for { <https://semopenalex.org/work/W2182930110> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W2182930110 abstract "Bag-of-Word based model is one of the state-of-the-art approaches for object retrieval or also known as instance search problem. Although this model and its extensions are good for rich-textured objects, it is still unsolved for searching on textureless ones. In this paper, we propose to combine this model with Deformable Part Models object detector using late fusion technique to improve final result. To find the optimal weights for each type of query objects, we further propose to use a neural network to learn query features including object area, number of shared visual words to get optimal weights for each model. Experimental results on TRECVID Instance Search (INS) dataset with queries in INS2013 and INS2014 show that our proposed method significantly improves 18.48% and 14.63% in mAP respectively comparing to standard BOW model and outperform other state-of-the-art methods. This method opens a new way of adaptively combining DPM, an object detector, in a hybrid model for visual instance search." @default.
- W2182930110 created "2016-06-24" @default.
- W2182930110 creator A5006166354 @default.
- W2182930110 creator A5043063578 @default.
- W2182930110 creator A5053495766 @default.
- W2182930110 creator A5054588832 @default.
- W2182930110 creator A5061914075 @default.
- W2182930110 creator A5078878666 @default.
- W2182930110 date "2015-10-01" @default.
- W2182930110 modified "2023-10-16" @default.
- W2182930110 title "Query-adaptive late fusion with neural network for instance search" @default.
- W2182930110 cites W124653583 @default.
- W2182930110 cites W1556531089 @default.
- W2182930110 cites W1967632700 @default.
- W2182930110 cites W1998157698 @default.
- W2182930110 cites W2056968687 @default.
- W2182930110 cites W2062903088 @default.
- W2182930110 cites W2065296697 @default.
- W2182930110 cites W2117848735 @default.
- W2182930110 cites W2122833801 @default.
- W2182930110 cites W2122934855 @default.
- W2182930110 cites W2126574503 @default.
- W2182930110 cites W2131846894 @default.
- W2182930110 cites W2141362318 @default.
- W2182930110 cites W2148809531 @default.
- W2182930110 cites W2151103935 @default.
- W2182930110 cites W2168356304 @default.
- W2182930110 cites W2172188317 @default.
- W2182930110 cites W2272000905 @default.
- W2182930110 doi "https://doi.org/10.1109/mmsp.2015.7340795" @default.
- W2182930110 hasPublicationYear "2015" @default.
- W2182930110 type Work @default.
- W2182930110 sameAs 2182930110 @default.
- W2182930110 citedByCount "3" @default.
- W2182930110 countsByYear W21829301102016 @default.
- W2182930110 countsByYear W21829301102017 @default.
- W2182930110 countsByYear W21829301102019 @default.
- W2182930110 crossrefType "proceedings-article" @default.
- W2182930110 hasAuthorship W2182930110A5006166354 @default.
- W2182930110 hasAuthorship W2182930110A5043063578 @default.
- W2182930110 hasAuthorship W2182930110A5053495766 @default.
- W2182930110 hasAuthorship W2182930110A5054588832 @default.
- W2182930110 hasAuthorship W2182930110A5061914075 @default.
- W2182930110 hasAuthorship W2182930110A5078878666 @default.
- W2182930110 hasConcept C11413529 @default.
- W2182930110 hasConcept C124101348 @default.
- W2182930110 hasConcept C153180895 @default.
- W2182930110 hasConcept C154945302 @default.
- W2182930110 hasConcept C2776151529 @default.
- W2182930110 hasConcept C2781238097 @default.
- W2182930110 hasConcept C41008148 @default.
- W2182930110 hasConcept C48103436 @default.
- W2182930110 hasConcept C50644808 @default.
- W2182930110 hasConcept C76155785 @default.
- W2182930110 hasConcept C94915269 @default.
- W2182930110 hasConceptScore W2182930110C11413529 @default.
- W2182930110 hasConceptScore W2182930110C124101348 @default.
- W2182930110 hasConceptScore W2182930110C153180895 @default.
- W2182930110 hasConceptScore W2182930110C154945302 @default.
- W2182930110 hasConceptScore W2182930110C2776151529 @default.
- W2182930110 hasConceptScore W2182930110C2781238097 @default.
- W2182930110 hasConceptScore W2182930110C41008148 @default.
- W2182930110 hasConceptScore W2182930110C48103436 @default.
- W2182930110 hasConceptScore W2182930110C50644808 @default.
- W2182930110 hasConceptScore W2182930110C76155785 @default.
- W2182930110 hasConceptScore W2182930110C94915269 @default.
- W2182930110 hasLocation W21829301101 @default.
- W2182930110 hasOpenAccess W2182930110 @default.
- W2182930110 hasPrimaryLocation W21829301101 @default.
- W2182930110 hasRelatedWork W2095705906 @default.
- W2182930110 hasRelatedWork W2801801420 @default.
- W2182930110 hasRelatedWork W2922421953 @default.
- W2182930110 hasRelatedWork W2970686063 @default.
- W2182930110 hasRelatedWork W2975200075 @default.
- W2182930110 hasRelatedWork W2998858795 @default.
- W2182930110 hasRelatedWork W3160733999 @default.
- W2182930110 hasRelatedWork W3187859696 @default.
- W2182930110 hasRelatedWork W4225418833 @default.
- W2182930110 hasRelatedWork W4321843798 @default.
- W2182930110 isParatext "false" @default.
- W2182930110 isRetracted "false" @default.
- W2182930110 magId "2182930110" @default.
- W2182930110 workType "article" @default.