Matches in SemOpenAlex for { <https://semopenalex.org/work/W2997138427> ?p ?o ?g. }
- W2997138427 endingPage "5432" @default.
- W2997138427 startingPage "5423" @default.
- W2997138427 abstract "In this article, a multiscale generative adversarial network (MS-GAN) is proposed for generating high-quality crowd density maps of arbitrary crowd density scenes. The task of crowd counting has many challenges, such as severe occlusions in extremely dense crowd scenes, perspective distortion, and high visual similarity between the pedestrians and background elements. To address these problems, the proposed MS-GAN combines a multiscale convolutional neural network (generator) and an adversarial network (discriminator) to generate a high-quality density map and accurately estimate the crowd count in complex crowd scenes. The multiscale generator utilizes the fusion features from multiple hierarchical layers to detect people with large-scale variation. The resulting density map produced by the multiscale generator is processed by a discriminator network trained to solve a binary classification task between a poor quality density map and real ground-truth ones. The additional adversarial loss can improve the quality of the density map, which is critical to accurately estimate the crowd counts. The experiments were conducted on multiple datasets with different crowd scenes and densities. The results showed that the proposed method provided better performance compared to current state-of-the-art methods." @default.
- W2997138427 created "2020-01-10" @default.
- W2997138427 creator A5001454737 @default.
- W2997138427 creator A5014854303 @default.
- W2997138427 creator A5067013431 @default.
- W2997138427 creator A5072714962 @default.
- W2997138427 creator A5079557669 @default.
- W2997138427 date "2021-11-01" @default.
- W2997138427 modified "2023-10-18" @default.
- W2997138427 title "Adversarial Learning for Multiscale Crowd Counting Under Complex Scenes" @default.
- W2997138427 cites W1910776219 @default.
- W2997138427 cites W1976959044 @default.
- W2997138427 cites W2013039598 @default.
- W2997138427 cites W2072232009 @default.
- W2997138427 cites W2088929512 @default.
- W2997138427 cites W2121864252 @default.
- W2997138427 cites W2123175289 @default.
- W2997138427 cites W2130751540 @default.
- W2997138427 cites W2130822989 @default.
- W2997138427 cites W2138948290 @default.
- W2997138427 cites W2151666244 @default.
- W2997138427 cites W2154946129 @default.
- W2997138427 cites W2158979073 @default.
- W2997138427 cites W2161969291 @default.
- W2997138427 cites W2165368973 @default.
- W2997138427 cites W2169671170 @default.
- W2997138427 cites W2313810099 @default.
- W2997138427 cites W2343818649 @default.
- W2997138427 cites W2394843433 @default.
- W2997138427 cites W2439881727 @default.
- W2997138427 cites W2463631526 @default.
- W2997138427 cites W2517615595 @default.
- W2997138427 cites W2519536754 @default.
- W2997138427 cites W2612114597 @default.
- W2997138427 cites W2625219738 @default.
- W2997138427 cites W2729018917 @default.
- W2997138427 cites W2745597836 @default.
- W2997138427 cites W2789524952 @default.
- W2997138427 cites W2793254521 @default.
- W2997138427 cites W2797761794 @default.
- W2997138427 cites W2798490576 @default.
- W2997138427 cites W2804059158 @default.
- W2997138427 cites W2901694823 @default.
- W2997138427 cites W2902078645 @default.
- W2997138427 cites W2945007989 @default.
- W2997138427 cites W2964307651 @default.
- W2997138427 cites W3097096317 @default.
- W2997138427 cites W3102632104 @default.
- W2997138427 cites W969788129 @default.
- W2997138427 doi "https://doi.org/10.1109/tcyb.2019.2956091" @default.
- W2997138427 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/31905157" @default.
- W2997138427 hasPublicationYear "2021" @default.
- W2997138427 type Work @default.
- W2997138427 sameAs 2997138427 @default.
- W2997138427 citedByCount "22" @default.
- W2997138427 countsByYear W29971384272019 @default.
- W2997138427 countsByYear W29971384272020 @default.
- W2997138427 countsByYear W29971384272021 @default.
- W2997138427 countsByYear W29971384272022 @default.
- W2997138427 countsByYear W29971384272023 @default.
- W2997138427 crossrefType "journal-article" @default.
- W2997138427 hasAuthorship W2997138427A5001454737 @default.
- W2997138427 hasAuthorship W2997138427A5014854303 @default.
- W2997138427 hasAuthorship W2997138427A5067013431 @default.
- W2997138427 hasAuthorship W2997138427A5072714962 @default.
- W2997138427 hasAuthorship W2997138427A5079557669 @default.
- W2997138427 hasConcept C115961682 @default.
- W2997138427 hasConcept C121332964 @default.
- W2997138427 hasConcept C126780896 @default.
- W2997138427 hasConcept C12713177 @default.
- W2997138427 hasConcept C146849305 @default.
- W2997138427 hasConcept C153180895 @default.
- W2997138427 hasConcept C154945302 @default.
- W2997138427 hasConcept C162324750 @default.
- W2997138427 hasConcept C163258240 @default.
- W2997138427 hasConcept C187736073 @default.
- W2997138427 hasConcept C194257627 @default.
- W2997138427 hasConcept C2776257435 @default.
- W2997138427 hasConcept C2779803651 @default.
- W2997138427 hasConcept C2780451532 @default.
- W2997138427 hasConcept C2780992000 @default.
- W2997138427 hasConcept C2988773926 @default.
- W2997138427 hasConcept C31258907 @default.
- W2997138427 hasConcept C31972630 @default.
- W2997138427 hasConcept C33923547 @default.
- W2997138427 hasConcept C37736160 @default.
- W2997138427 hasConcept C41008148 @default.
- W2997138427 hasConcept C48372109 @default.
- W2997138427 hasConcept C62520636 @default.
- W2997138427 hasConcept C76155785 @default.
- W2997138427 hasConcept C81363708 @default.
- W2997138427 hasConcept C94375191 @default.
- W2997138427 hasConcept C94915269 @default.
- W2997138427 hasConceptScore W2997138427C115961682 @default.
- W2997138427 hasConceptScore W2997138427C121332964 @default.
- W2997138427 hasConceptScore W2997138427C126780896 @default.
- W2997138427 hasConceptScore W2997138427C12713177 @default.
- W2997138427 hasConceptScore W2997138427C146849305 @default.