FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2892882960> ?p ?o ?g. }

• W2892882960 abstract "Abstract Motion information can be important for detecting objects, but it has been used less for pedestrian detection, particularly with deep-learning-based methods. We propose a method that uses deep motion features as well as deep still-image features, following the success of two-stream convolutional networks, each of which are trained separately for spatial and temporal streams. To extract motion clues for detection differentiated from other background motions, the temporal stream takes as input the difference in frames that are weakly stabilized by optical flow. To make the networks applicable to bounding-box-level detection, the mid-level features are concatenated and combined with a sliding-window detector. We also introduce transfer learning from multiple sources in the two-stream networks, which can transfer still image and motion features from ImageNet and an action recognition dataset respectively, to overcome the insufficiency of training data for convolutional neural networks in pedestrian datasets. We conducted an evaluation on two popular large-scale pedestrian benchmarks, namely the Caltech Pedestrian Detection Benchmark and Daimler Mono Pedestrian Detection Benchmark. We observed 10% improvement compared to the same method but without motion features." @default.
• W2892882960 created "2018-10-05" @default.
• W2892882960 creator A5003277535 @default.
• W2892882960 creator A5006134569 @default.
• W2892882960 creator A5026866776 @default.
• W2892882960 creator A5062487802 @default.
• W2892882960 creator A5067212480 @default.
• W2892882960 creator A5069342829 @default.
• W2892882960 date "2018-09-27" @default.
• W2892882960 modified "2023-10-07" @default.
• W2892882960 title "Pedestrian detection with motion features via two-stream ConvNets" @default.
• W2892882960 cites W1230023165 @default.
• W2892882960 cites W1475617732 @default.
• W2892882960 cites W1499780422 @default.
• W2892882960 cites W1574719918 @default.
• W2892882960 cites W1574818812 @default.
• W2892882960 cites W1586730761 @default.
• W2892882960 cites W1595717062 @default.
• W2892882960 cites W1744759976 @default.
• W2892882960 cites W1903029394 @default.
• W2892882960 cites W1903127635 @default.
• W2892882960 cites W1923332106 @default.
• W2892882960 cites W1944615693 @default.
• W2892882960 cites W1955857676 @default.
• W2892882960 cites W1960289438 @default.
• W2892882960 cites W1962468782 @default.
• W2892882960 cites W1976818984 @default.
• W2892882960 cites W1983364832 @default.
• W2892882960 cites W1999192586 @default.
• W2892882960 cites W1999853363 @default.
• W2892882960 cites W2016053056 @default.
• W2892882960 cites W2019377328 @default.
• W2892882960 cites W2031454541 @default.
• W2892882960 cites W2037227137 @default.
• W2892882960 cites W2074777933 @default.
• W2892882960 cites W2082627290 @default.
• W2892882960 cites W2084997728 @default.
• W2892882960 cites W2096691069 @default.
• W2892882960 cites W2097117768 @default.
• W2892882960 cites W2099634219 @default.
• W2892882960 cites W2102605133 @default.
• W2892882960 cites W2107775979 @default.
• W2892882960 cites W2113221323 @default.
• W2892882960 cites W2115471590 @default.
• W2892882960 cites W2116022929 @default.
• W2892882960 cites W2117539524 @default.
• W2892882960 cites W2117687030 @default.
• W2892882960 cites W2120419212 @default.
• W2892882960 cites W2124386111 @default.
• W2892882960 cites W2125066085 @default.
• W2892882960 cites W2125556102 @default.
• W2892882960 cites W2135825553 @default.
• W2892882960 cites W2138302688 @default.
• W2892882960 cites W2139479830 @default.
• W2892882960 cites W2140317610 @default.
• W2892882960 cites W2155893237 @default.
• W2892882960 cites W2156547346 @default.
• W2892882960 cites W2162741153 @default.
• W2892882960 cites W2179352600 @default.
• W2892882960 cites W2200528286 @default.
• W2892882960 cites W2490270993 @default.
• W2892882960 cites W2497039038 @default.
• W2892882960 cites W2548197316 @default.
• W2892882960 cites W2552900565 @default.
• W2892882960 cites W255708204 @default.
• W2892882960 cites W2576085163 @default.
• W2892882960 cites W2578555672 @default.
• W2892882960 cites W2609046027 @default.
• W2892882960 cites W2613599172 @default.
• W2892882960 cites W2911964244 @default.
• W2892882960 cites W2962855257 @default.
• W2892882960 cites W2964286567 @default.
• W2892882960 cites W3151111735 @default.
• W2892882960 cites W345900524 @default.
• W2892882960 cites W4248437541 @default.
• W2892882960 doi "https://doi.org/10.1186/s41074-018-0048-5" @default.
• W2892882960 hasPublicationYear "2018" @default.
• W2892882960 type Work @default.
• W2892882960 sameAs 2892882960 @default.
• W2892882960 citedByCount "5" @default.
• W2892882960 countsByYear W28928829602020 @default.
• W2892882960 countsByYear W28928829602021 @default.
• W2892882960 countsByYear W28928829602022 @default.
• W2892882960 countsByYear W28928829602023 @default.
• W2892882960 crossrefType "journal-article" @default.
• W2892882960 hasAuthorship W2892882960A5003277535 @default.
• W2892882960 hasAuthorship W2892882960A5006134569 @default.
• W2892882960 hasAuthorship W2892882960A5026866776 @default.
• W2892882960 hasAuthorship W2892882960A5062487802 @default.
• W2892882960 hasAuthorship W2892882960A5067212480 @default.
• W2892882960 hasAuthorship W2892882960A5069342829 @default.
• W2892882960 hasBestOaLocation W28928829601 @default.
• W2892882960 hasConcept C102392041 @default.
• W2892882960 hasConcept C104114177 @default.
• W2892882960 hasConcept C108583219 @default.
• W2892882960 hasConcept C111919701 @default.
• W2892882960 hasConcept C115961682 @default.
• W2892882960 hasConcept C127413603 @default.
• W2892882960 hasConcept C13280743 @default.
• W2892882960 hasConcept C147037132 @default.

• next