Matches in SemOpenAlex for { <https://semopenalex.org/work/W3204130207> ?p ?o ?g. }
- W3204130207 endingPage "136044" @default.
- W3204130207 startingPage "136032" @default.
- W3204130207 abstract "Huge variations in the scales of people in images create an extremely challenging problem in the task of crowd counting. Currently, many researchers apply multi-column structures to solve the scale variation problem. However, multi-column structures usually have complex structures with large numbers of parameters and are difficult to optimize. To this end, we propose a scale-aware representation learning network (SRNet) that uses a commonly used encoder-decoder framework. An image is converted into deep features by the first ten layers of VGG16 in the encoder. Then, the features are regressed to a crowd density map via the decoder. The decoder mainly consists of two modules: the scale-aware feature learning module (SAM) and the pixel-aware upsampling module (PAM). SAM models the multi-scale features of a crowd at each level with different sizes of receptive fields, and PAM enlarges the spatial resolution and enhances the pixel-level semantic information, thereby improving the overall counting accuracy. We conduct extensive crowd counting experiments on ShanghaiTech Part_A, UCF-QNRF, and UCF_CC_50 datasets. Furthermore, to obtain the locations of each person, we conduct crowd localization experiments on UCF-QNRF and NWPU-Crowd datasets. The qualitative and quantitative results prove the effectiveness of the SRNet in dense crowd counting and crowd localization tasks." @default.
- W3204130207 created "2021-10-11" @default.
- W3204130207 creator A5006247366 @default.
- W3204130207 creator A5017852951 @default.
- W3204130207 creator A5025851882 @default.
- W3204130207 creator A5054187716 @default.
- W3204130207 creator A5067903239 @default.
- W3204130207 date "2021-01-01" @default.
- W3204130207 modified "2023-10-18" @default.
- W3204130207 title "SRNet: Scale-Aware Representation Learning Network for Dense Crowd Counting" @default.
- W3204130207 cites W1901129140 @default.
- W3204130207 cites W1910776219 @default.
- W3204130207 cites W1978232622 @default.
- W3204130207 cites W1992825118 @default.
- W3204130207 cites W2013039598 @default.
- W3204130207 cites W2058907003 @default.
- W3204130207 cites W2065994824 @default.
- W3204130207 cites W2072232009 @default.
- W3204130207 cites W2109255472 @default.
- W3204130207 cites W2123175289 @default.
- W3204130207 cites W2161969291 @default.
- W3204130207 cites W2168356304 @default.
- W3204130207 cites W2194775991 @default.
- W3204130207 cites W2197234429 @default.
- W3204130207 cites W2207893099 @default.
- W3204130207 cites W2412782625 @default.
- W3204130207 cites W2463631526 @default.
- W3204130207 cites W2541389513 @default.
- W3204130207 cites W2579152745 @default.
- W3204130207 cites W2586716774 @default.
- W3204130207 cites W2613599172 @default.
- W3204130207 cites W2741077351 @default.
- W3204130207 cites W2798490576 @default.
- W3204130207 cites W2798781811 @default.
- W3204130207 cites W2886443245 @default.
- W3204130207 cites W2892664578 @default.
- W3204130207 cites W2916870778 @default.
- W3204130207 cites W2922282711 @default.
- W3204130207 cites W2922295717 @default.
- W3204130207 cites W2942021360 @default.
- W3204130207 cites W2945007989 @default.
- W3204130207 cites W2945574898 @default.
- W3204130207 cites W2945582636 @default.
- W3204130207 cites W2948513880 @default.
- W3204130207 cites W2962720716 @default.
- W3204130207 cites W2963035940 @default.
- W3204130207 cites W2963315052 @default.
- W3204130207 cites W2963404857 @default.
- W3204130207 cites W2963446712 @default.
- W3204130207 cites W2963893037 @default.
- W3204130207 cites W2964203052 @default.
- W3204130207 cites W2964209782 @default.
- W3204130207 cites W2964503501 @default.
- W3204130207 cites W2966271765 @default.
- W3204130207 cites W2966298261 @default.
- W3204130207 cites W2966893608 @default.
- W3204130207 cites W2967069910 @default.
- W3204130207 cites W2967776630 @default.
- W3204130207 cites W2969620138 @default.
- W3204130207 cites W2970588228 @default.
- W3204130207 cites W2981436300 @default.
- W3204130207 cites W2982021328 @default.
- W3204130207 cites W2987988567 @default.
- W3204130207 cites W2994401994 @default.
- W3204130207 cites W2995582330 @default.
- W3204130207 cites W2996000181 @default.
- W3204130207 cites W2996703886 @default.
- W3204130207 cites W2997138427 @default.
- W3204130207 cites W2997996590 @default.
- W3204130207 cites W3010021361 @default.
- W3204130207 cites W3024476684 @default.
- W3204130207 cites W3027606690 @default.
- W3204130207 cites W3035028692 @default.
- W3204130207 cites W3046161527 @default.
- W3204130207 cites W3083955366 @default.
- W3204130207 cites W3084883754 @default.
- W3204130207 cites W3090067631 @default.
- W3204130207 cites W3102632104 @default.
- W3204130207 cites W3106949330 @default.
- W3204130207 cites W3107554785 @default.
- W3204130207 cites W3109272290 @default.
- W3204130207 cites W3127995199 @default.
- W3204130207 cites W607748843 @default.
- W3204130207 doi "https://doi.org/10.1109/access.2021.3115963" @default.
- W3204130207 hasPublicationYear "2021" @default.
- W3204130207 type Work @default.
- W3204130207 sameAs 3204130207 @default.
- W3204130207 citedByCount "4" @default.
- W3204130207 countsByYear W32041302072022 @default.
- W3204130207 countsByYear W32041302072023 @default.
- W3204130207 crossrefType "journal-article" @default.
- W3204130207 hasAuthorship W3204130207A5006247366 @default.
- W3204130207 hasAuthorship W3204130207A5017852951 @default.
- W3204130207 hasAuthorship W3204130207A5025851882 @default.
- W3204130207 hasAuthorship W3204130207A5054187716 @default.
- W3204130207 hasAuthorship W3204130207A5067903239 @default.
- W3204130207 hasBestOaLocation W32041302071 @default.
- W3204130207 hasConcept C108583219 @default.