Matches in SemOpenAlex for { <https://semopenalex.org/work/W3207203470> ?p ?o ?g. }
Showing items 1 to 84 of
84
with 100 items per page.
- W3207203470 abstract "Vehicle counting aims to calculate the number of vehicles in congested traffic scenes. Although object detection and crowd counting have made tremendous progress with the development of deep learning, vehicle counting remains a challenging task, due to scale variations, viewpoint changes, inconsistent location distributions, diverse visual appearances and severe occlusions. In this paper, a well-designed Vehicle Counting Network (VCNet) is novelly proposed to alleviate the problem of scale variation and inconsistent spatial distribution in congested traffic scenes. Specifically, VCNet is composed of two major components: (i) To capture multi-scale vehicles across different types and camera viewpoints, an effective multi-scale density map estimation structure is designed by building an attention-based mask refinement module. The multi-branch structure with hybrid dilated convolution blocks is proposed to assign receptive fields to generate multi-scale density maps. To efficiently aggregate multi-scale density maps, the attention-based mask refinement is well-designed to highlight the vehicle regions, which enables each branch to suppress the scale interference from other branches. (ii) In order to capture the inconsistent spatial distributions, a spatial-awareness block loss (SBL) based on the region-weighted reward strategy is proposed to calculate the loss of different spatial regions including sparse, congested and occluded regions independently by dividing the density map into different regions. Extensive experiments conducted on three benchmark datasets, TRANCOS, VisDrone2019 Vehicle and CVCSet demonstrate that the proposed VCNet outperforms the state-of-the-art approaches in vehicle counting. Moreover, the proposed idea can be applicable for crowd counting, which produces competitive results on ShanghaiTech crowd counting dataset." @default.
- W3207203470 created "2021-10-25" @default.
- W3207203470 creator A5011680564 @default.
- W3207203470 creator A5045727713 @default.
- W3207203470 creator A5046968984 @default.
- W3207203470 creator A5051540922 @default.
- W3207203470 date "2021-10-17" @default.
- W3207203470 modified "2023-09-24" @default.
- W3207203470 title "Vehicle Counting Network with Attention-based Mask Refinement and Spatial-awareness Block Loss" @default.
- W3207203470 cites W1910776219 @default.
- W3207203470 cites W2013039598 @default.
- W3207203470 cites W2031454541 @default.
- W3207203470 cites W2120815373 @default.
- W3207203470 cites W2155916750 @default.
- W3207203470 cites W2463631526 @default.
- W3207203470 cites W2520826941 @default.
- W3207203470 cites W2592939477 @default.
- W3207203470 cites W2884585870 @default.
- W3207203470 cites W2915476573 @default.
- W3207203470 cites W2962832028 @default.
- W3207203470 cites W2962854645 @default.
- W3207203470 cites W2962921175 @default.
- W3207203470 cites W2963150697 @default.
- W3207203470 cites W2963179609 @default.
- W3207203470 cites W2963351448 @default.
- W3207203470 cites W2963838390 @default.
- W3207203470 cites W2963893037 @default.
- W3207203470 cites W2964046724 @default.
- W3207203470 cites W2964209782 @default.
- W3207203470 cites W2967069910 @default.
- W3207203470 cites W2967776630 @default.
- W3207203470 cites W2969620138 @default.
- W3207203470 cites W2981766846 @default.
- W3207203470 cites W2982021328 @default.
- W3207203470 cites W2982770724 @default.
- W3207203470 cites W2989611864 @default.
- W3207203470 cites W2991359031 @default.
- W3207203470 cites W2992214693 @default.
- W3207203470 cites W2995582330 @default.
- W3207203470 cites W3004672782 @default.
- W3207203470 cites W3010021361 @default.
- W3207203470 cites W3011692687 @default.
- W3207203470 cites W3035193053 @default.
- W3207203470 cites W3035307763 @default.
- W3207203470 cites W3084883754 @default.
- W3207203470 cites W3093161755 @default.
- W3207203470 cites W3106250896 @default.
- W3207203470 doi "https://doi.org/10.1145/3474085.3475246" @default.
- W3207203470 hasPublicationYear "2021" @default.
- W3207203470 type Work @default.
- W3207203470 sameAs 3207203470 @default.
- W3207203470 citedByCount "1" @default.
- W3207203470 countsByYear W32072034702022 @default.
- W3207203470 crossrefType "proceedings-article" @default.
- W3207203470 hasAuthorship W3207203470A5011680564 @default.
- W3207203470 hasAuthorship W3207203470A5045727713 @default.
- W3207203470 hasAuthorship W3207203470A5046968984 @default.
- W3207203470 hasAuthorship W3207203470A5051540922 @default.
- W3207203470 hasConcept C2524010 @default.
- W3207203470 hasConcept C2777210771 @default.
- W3207203470 hasConcept C33923547 @default.
- W3207203470 hasConcept C41008148 @default.
- W3207203470 hasConceptScore W3207203470C2524010 @default.
- W3207203470 hasConceptScore W3207203470C2777210771 @default.
- W3207203470 hasConceptScore W3207203470C33923547 @default.
- W3207203470 hasConceptScore W3207203470C41008148 @default.
- W3207203470 hasFunder F4320334062 @default.
- W3207203470 hasLocation W32072034701 @default.
- W3207203470 hasOpenAccess W3207203470 @default.
- W3207203470 hasPrimaryLocation W32072034701 @default.
- W3207203470 hasRelatedWork W1516180252 @default.
- W3207203470 hasRelatedWork W1991645212 @default.
- W3207203470 hasRelatedWork W2026169332 @default.
- W3207203470 hasRelatedWork W2060603879 @default.
- W3207203470 hasRelatedWork W2348954130 @default.
- W3207203470 hasRelatedWork W2355215981 @default.
- W3207203470 hasRelatedWork W2383869160 @default.
- W3207203470 hasRelatedWork W2463753533 @default.
- W3207203470 hasRelatedWork W2558743939 @default.
- W3207203470 hasRelatedWork W3052481912 @default.
- W3207203470 isParatext "false" @default.
- W3207203470 isRetracted "false" @default.
- W3207203470 magId "3207203470" @default.
- W3207203470 workType "article" @default.