Matches in SemOpenAlex for { <https://semopenalex.org/work/W4220996815> ?p ?o ?g. }
- W4220996815 endingPage "20560" @default.
- W4220996815 startingPage "20541" @default.
- W4220996815 abstract "Accurately modeling the crowd’s head scale variations is an effective way to improve the counting accuracy of the crowd counting methods. Most counting networks apply a multi-branch network structure to obtain different scales of head features. Although they have achieved promising results, they do not perform very well on the extreme scale variation scene due to the limited scale representability. Meanwhile, these methods are prone to recognize background objects as foreground crowds in complex scenes due to the limited context and high-level semantic information. We propose a compositional multi-scale feature enhanced learning approach (COMAL) for crowd counting to handle the above limitations. COMAL enhances the multi-scale feature representations from three aspects: (1) The semantic enhanced module (SEM) is developed for embedding the high-level semantic information to the multi-scale features; (2) The diversity enhanced module (DEM) is proposed to enrich the variety of crowd features’ different scales; (3) The context enhanced module (CEM) is designed for strengthening the multi-scale features with more context information. Based on the proposed COMAL, we develop a crowd counting network under the encoder-decoder framework and perform extensive experiments on ShanghaiTech, UCF_CC_50, and UCF-QNRF datasets. Qualitative and quantitive results demonstrate the effectiveness of the proposed COMAL." @default.
- W4220996815 created "2022-04-03" @default.
- W4220996815 creator A5004305313 @default.
- W4220996815 creator A5011863170 @default.
- W4220996815 creator A5025851882 @default.
- W4220996815 creator A5028582304 @default.
- W4220996815 creator A5046735223 @default.
- W4220996815 creator A5049916114 @default.
- W4220996815 creator A5058411526 @default.
- W4220996815 date "2022-03-11" @default.
- W4220996815 modified "2023-10-18" @default.
- W4220996815 title "COMAL: compositional multi-scale feature enhanced learning for crowd counting" @default.
- W4220996815 cites W1910776219 @default.
- W4220996815 cites W1978232622 @default.
- W4220996815 cites W2016473469 @default.
- W4220996815 cites W2045494549 @default.
- W4220996815 cites W2072232009 @default.
- W4220996815 cites W2109255472 @default.
- W4220996815 cites W2123175289 @default.
- W4220996815 cites W2463631526 @default.
- W4220996815 cites W2517615595 @default.
- W4220996815 cites W2519281173 @default.
- W4220996815 cites W2560023338 @default.
- W4220996815 cites W2565639579 @default.
- W4220996815 cites W2592939477 @default.
- W4220996815 cites W2741077351 @default.
- W4220996815 cites W2767041499 @default.
- W4220996815 cites W2790571983 @default.
- W4220996815 cites W2798490576 @default.
- W4220996815 cites W2798781811 @default.
- W4220996815 cites W2883929025 @default.
- W4220996815 cites W2884585870 @default.
- W4220996815 cites W2884960332 @default.
- W4220996815 cites W2886443245 @default.
- W4220996815 cites W2895051362 @default.
- W4220996815 cites W2922282711 @default.
- W4220996815 cites W2922295717 @default.
- W4220996815 cites W2945574898 @default.
- W4220996815 cites W2948513880 @default.
- W4220996815 cites W2953433552 @default.
- W4220996815 cites W2963035940 @default.
- W4220996815 cites W2963815618 @default.
- W4220996815 cites W2963838390 @default.
- W4220996815 cites W2964046724 @default.
- W4220996815 cites W2964203052 @default.
- W4220996815 cites W2964209782 @default.
- W4220996815 cites W2964264515 @default.
- W4220996815 cites W2965391153 @default.
- W4220996815 cites W2966271765 @default.
- W4220996815 cites W2966893608 @default.
- W4220996815 cites W2967069910 @default.
- W4220996815 cites W2967776630 @default.
- W4220996815 cites W2969620138 @default.
- W4220996815 cites W2982021328 @default.
- W4220996815 cites W2982220924 @default.
- W4220996815 cites W2987761108 @default.
- W4220996815 cites W2990214144 @default.
- W4220996815 cites W2992214693 @default.
- W4220996815 cites W3008553320 @default.
- W4220996815 cites W3009238340 @default.
- W4220996815 cites W3017794714 @default.
- W4220996815 cites W3019808793 @default.
- W4220996815 cites W3024476684 @default.
- W4220996815 cites W3033675321 @default.
- W4220996815 cites W3048255366 @default.
- W4220996815 cites W3082125592 @default.
- W4220996815 cites W3090067631 @default.
- W4220996815 cites W3106732900 @default.
- W4220996815 cites W3106949330 @default.
- W4220996815 cites W3135364787 @default.
- W4220996815 doi "https://doi.org/10.1007/s11042-022-12249-9" @default.
- W4220996815 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/35291715" @default.
- W4220996815 hasPublicationYear "2022" @default.
- W4220996815 type Work @default.
- W4220996815 citedByCount "6" @default.
- W4220996815 countsByYear W42209968152022 @default.
- W4220996815 countsByYear W42209968152023 @default.
- W4220996815 crossrefType "journal-article" @default.
- W4220996815 hasAuthorship W4220996815A5004305313 @default.
- W4220996815 hasAuthorship W4220996815A5011863170 @default.
- W4220996815 hasAuthorship W4220996815A5025851882 @default.
- W4220996815 hasAuthorship W4220996815A5028582304 @default.
- W4220996815 hasAuthorship W4220996815A5046735223 @default.
- W4220996815 hasAuthorship W4220996815A5049916114 @default.
- W4220996815 hasAuthorship W4220996815A5058411526 @default.
- W4220996815 hasBestOaLocation W42209968151 @default.
- W4220996815 hasConcept C111919701 @default.
- W4220996815 hasConcept C118505674 @default.
- W4220996815 hasConcept C119857082 @default.
- W4220996815 hasConcept C121332964 @default.
- W4220996815 hasConcept C138885662 @default.
- W4220996815 hasConcept C151730666 @default.
- W4220996815 hasConcept C153180895 @default.
- W4220996815 hasConcept C154945302 @default.
- W4220996815 hasConcept C2776401178 @default.
- W4220996815 hasConcept C2777852691 @default.
- W4220996815 hasConcept C2778755073 @default.
- W4220996815 hasConcept C2779343474 @default.