Matches in SemOpenAlex for { <https://semopenalex.org/work/W2510184956> ?p ?o ?g. }
- W2510184956 endingPage "642" @default.
- W2510184956 startingPage "633" @default.
- W2510184956 abstract "Object tracking is a fundamental task for building vision systems of automatic transportation. Despite demonstrated success in this active research field, it is still difficult to cope with complicated appearance changes caused by background clutters, illumination change, scale variation, deformation, rotation, and occlusion, etc. Due to these challenging factors, a target bounding box tends to easily contain a disturbing context of background, which may lead to an inaccurate localization if some key parts of the foreground object share an excess of information loss. In this paper, we propose an online algorithm using the local loss features to alleviate the drift problem during tracking. An adaptive block-division appearance model is constructed to exploit patch-based loss representations by decomposing sample region sequences into a set of subblocks. The basic purpose of partition coefficients is to indicate local relevance and effectively capture spatial correlation through measuring image similarity. Namely, they can strengthen positive effects of discriminative patches within locating bounding boxes and weaken negative impacts of disturbing context possibly included in the surrounding regions. The object state estimation of a moving target is then formulated as an integrated likelihood evaluation on the ensemble loss. Experimental results on a suite of representative video sequences of realistic scenarios demonstrate the superiority of the proposed method to several state-of-the-art tracking approaches in terms of both accuracy and robustness." @default.
- W2510184956 created "2016-09-16" @default.
- W2510184956 creator A5005727907 @default.
- W2510184956 creator A5068837264 @default.
- W2510184956 creator A5075934214 @default.
- W2510184956 date "2017-03-01" @default.
- W2510184956 modified "2023-10-14" @default.
- W2510184956 title "Visual Object Tracking With Partition Loss Schemes" @default.
- W2510184956 cites W1849710887 @default.
- W2510184956 cites W1915599933 @default.
- W2510184956 cites W1966429191 @default.
- W2510184956 cites W1973890423 @default.
- W2510184956 cites W1977709942 @default.
- W2510184956 cites W1981219153 @default.
- W2510184956 cites W1982423097 @default.
- W2510184956 cites W1982764079 @default.
- W2510184956 cites W1984914017 @default.
- W2510184956 cites W2001785244 @default.
- W2510184956 cites W2020510457 @default.
- W2510184956 cites W2023622049 @default.
- W2510184956 cites W2050802469 @default.
- W2510184956 cites W2066513304 @default.
- W2510184956 cites W2080292705 @default.
- W2510184956 cites W2086383524 @default.
- W2510184956 cites W2089961441 @default.
- W2510184956 cites W2094919853 @default.
- W2510184956 cites W2100138625 @default.
- W2510184956 cites W2109579504 @default.
- W2510184956 cites W2109654411 @default.
- W2510184956 cites W2115900659 @default.
- W2510184956 cites W2117820313 @default.
- W2510184956 cites W2121193292 @default.
- W2510184956 cites W2121255229 @default.
- W2510184956 cites W2121362102 @default.
- W2510184956 cites W2123947647 @default.
- W2510184956 cites W2127575804 @default.
- W2510184956 cites W2127782573 @default.
- W2510184956 cites W2131076267 @default.
- W2510184956 cites W2132461991 @default.
- W2510184956 cites W2136119148 @default.
- W2510184956 cites W2137938359 @default.
- W2510184956 cites W2138273245 @default.
- W2510184956 cites W2152323237 @default.
- W2510184956 cites W2154429285 @default.
- W2510184956 cites W2156828505 @default.
- W2510184956 cites W2162508706 @default.
- W2510184956 cites W2165065922 @default.
- W2510184956 cites W2169566837 @default.
- W2510184956 cites W2179713099 @default.
- W2510184956 cites W2335586288 @default.
- W2510184956 cites W4249625263 @default.
- W2510184956 doi "https://doi.org/10.1109/tits.2016.2585663" @default.
- W2510184956 hasPublicationYear "2017" @default.
- W2510184956 type Work @default.
- W2510184956 sameAs 2510184956 @default.
- W2510184956 citedByCount "10" @default.
- W2510184956 countsByYear W25101849562019 @default.
- W2510184956 countsByYear W25101849562020 @default.
- W2510184956 countsByYear W25101849562021 @default.
- W2510184956 countsByYear W25101849562022 @default.
- W2510184956 crossrefType "journal-article" @default.
- W2510184956 hasAuthorship W2510184956A5005727907 @default.
- W2510184956 hasAuthorship W2510184956A5068837264 @default.
- W2510184956 hasAuthorship W2510184956A5075934214 @default.
- W2510184956 hasConcept C114614502 @default.
- W2510184956 hasConcept C154945302 @default.
- W2510184956 hasConcept C202474056 @default.
- W2510184956 hasConcept C2781238097 @default.
- W2510184956 hasConcept C31972630 @default.
- W2510184956 hasConcept C33923547 @default.
- W2510184956 hasConcept C41008148 @default.
- W2510184956 hasConcept C42812 @default.
- W2510184956 hasConceptScore W2510184956C114614502 @default.
- W2510184956 hasConceptScore W2510184956C154945302 @default.
- W2510184956 hasConceptScore W2510184956C202474056 @default.
- W2510184956 hasConceptScore W2510184956C2781238097 @default.
- W2510184956 hasConceptScore W2510184956C31972630 @default.
- W2510184956 hasConceptScore W2510184956C33923547 @default.
- W2510184956 hasConceptScore W2510184956C41008148 @default.
- W2510184956 hasConceptScore W2510184956C42812 @default.
- W2510184956 hasFunder F4320321001 @default.
- W2510184956 hasFunder F4320335777 @default.
- W2510184956 hasIssue "3" @default.
- W2510184956 hasLocation W25101849561 @default.
- W2510184956 hasOpenAccess W2510184956 @default.
- W2510184956 hasPrimaryLocation W25101849561 @default.
- W2510184956 hasRelatedWork W1487175407 @default.
- W2510184956 hasRelatedWork W2040965325 @default.
- W2510184956 hasRelatedWork W2068395580 @default.
- W2510184956 hasRelatedWork W2343908003 @default.
- W2510184956 hasRelatedWork W2385949326 @default.
- W2510184956 hasRelatedWork W2510317309 @default.
- W2510184956 hasRelatedWork W2534746541 @default.
- W2510184956 hasRelatedWork W2789220062 @default.
- W2510184956 hasRelatedWork W2820058250 @default.
- W2510184956 hasRelatedWork W2185534064 @default.
- W2510184956 hasVolume "18" @default.
- W2510184956 isParatext "false" @default.