Matches in SemOpenAlex for { <https://semopenalex.org/work/W3146025091> ?p ?o ?g. }
Showing items 1 to 97 of
97
with 100 items per page.
- W3146025091 abstract "Crowd counting aims to predict the number of people and generate the density map in the image. There are many challenges, including varying head scales, the diversity of crowd distribution across images and cluttered backgrounds. In this paper, we propose a multi-scale context aggregation network (MSCANet) based on single-column encoder-decoder architecture for crowd counting, which consists of an encoder based on a dense context-aware module (DCAM) and a hierarchical attention-guided decoder. To handle the issue of scale variation, we construct the DCAM to aggregate multi-scale contextual information by densely connecting the dilated convolution with varying receptive fields. The proposed DCAM can capture rich contextual information of crowd areas due to its long-range receptive fields and dense scale sampling. Moreover, to suppress the background noise and generate a high-quality density map, we adopt a hierarchical attention-guided mechanism in the decoder. This helps to integrate more useful spatial information from shallow feature maps of the encoder by introducing multiple supervision based on semantic attention module (SAM). Extensive experiments demonstrate that the proposed approach achieves better performance than other similar state-of-the-art methods on three challenging benchmark datasets for crowd counting. The code is available at https://github.com/KingMV/MSCANet" @default.
- W3146025091 created "2021-04-13" @default.
- W3146025091 creator A5006822602 @default.
- W3146025091 creator A5013822484 @default.
- W3146025091 creator A5023796538 @default.
- W3146025091 creator A5062706107 @default.
- W3146025091 date "2021-04-05" @default.
- W3146025091 modified "2023-09-24" @default.
- W3146025091 title "Multi-Scale Context Aggregation Network with Attention-Guided for Crowd Counting" @default.
- W3146025091 cites W1686810756 @default.
- W3146025091 cites W1901129140 @default.
- W3146025091 cites W2463631526 @default.
- W3146025091 cites W2565639579 @default.
- W3146025091 cites W2741077351 @default.
- W3146025091 cites W2895051362 @default.
- W3146025091 cites W2922295717 @default.
- W3146025091 cites W2945574898 @default.
- W3146025091 cites W2963893037 @default.
- W3146025091 cites W2964203052 @default.
- W3146025091 cites W2964209782 @default.
- W3146025091 cites W2967069910 @default.
- W3146025091 cites W2975784364 @default.
- W3146025091 cites W2987761108 @default.
- W3146025091 cites W2994401994 @default.
- W3146025091 cites W2995580282 @default.
- W3146025091 cites W3013987429 @default.
- W3146025091 cites W3015395800 @default.
- W3146025091 doi "https://doi.org/10.48550/arxiv.2104.02245" @default.
- W3146025091 hasPublicationYear "2021" @default.
- W3146025091 type Work @default.
- W3146025091 sameAs 3146025091 @default.
- W3146025091 citedByCount "0" @default.
- W3146025091 crossrefType "posted-content" @default.
- W3146025091 hasAuthorship W3146025091A5006822602 @default.
- W3146025091 hasAuthorship W3146025091A5013822484 @default.
- W3146025091 hasAuthorship W3146025091A5023796538 @default.
- W3146025091 hasAuthorship W3146025091A5062706107 @default.
- W3146025091 hasBestOaLocation W31460250911 @default.
- W3146025091 hasConcept C111919701 @default.
- W3146025091 hasConcept C118505674 @default.
- W3146025091 hasConcept C121332964 @default.
- W3146025091 hasConcept C124101348 @default.
- W3146025091 hasConcept C13280743 @default.
- W3146025091 hasConcept C151730666 @default.
- W3146025091 hasConcept C153180895 @default.
- W3146025091 hasConcept C154945302 @default.
- W3146025091 hasConcept C159985019 @default.
- W3146025091 hasConcept C177264268 @default.
- W3146025091 hasConcept C185798385 @default.
- W3146025091 hasConcept C192562407 @default.
- W3146025091 hasConcept C199360897 @default.
- W3146025091 hasConcept C205649164 @default.
- W3146025091 hasConcept C2776760102 @default.
- W3146025091 hasConcept C2778755073 @default.
- W3146025091 hasConcept C2779343474 @default.
- W3146025091 hasConcept C41008148 @default.
- W3146025091 hasConcept C4679612 @default.
- W3146025091 hasConcept C62520636 @default.
- W3146025091 hasConcept C86803240 @default.
- W3146025091 hasConceptScore W3146025091C111919701 @default.
- W3146025091 hasConceptScore W3146025091C118505674 @default.
- W3146025091 hasConceptScore W3146025091C121332964 @default.
- W3146025091 hasConceptScore W3146025091C124101348 @default.
- W3146025091 hasConceptScore W3146025091C13280743 @default.
- W3146025091 hasConceptScore W3146025091C151730666 @default.
- W3146025091 hasConceptScore W3146025091C153180895 @default.
- W3146025091 hasConceptScore W3146025091C154945302 @default.
- W3146025091 hasConceptScore W3146025091C159985019 @default.
- W3146025091 hasConceptScore W3146025091C177264268 @default.
- W3146025091 hasConceptScore W3146025091C185798385 @default.
- W3146025091 hasConceptScore W3146025091C192562407 @default.
- W3146025091 hasConceptScore W3146025091C199360897 @default.
- W3146025091 hasConceptScore W3146025091C205649164 @default.
- W3146025091 hasConceptScore W3146025091C2776760102 @default.
- W3146025091 hasConceptScore W3146025091C2778755073 @default.
- W3146025091 hasConceptScore W3146025091C2779343474 @default.
- W3146025091 hasConceptScore W3146025091C41008148 @default.
- W3146025091 hasConceptScore W3146025091C4679612 @default.
- W3146025091 hasConceptScore W3146025091C62520636 @default.
- W3146025091 hasConceptScore W3146025091C86803240 @default.
- W3146025091 hasLocation W31460250911 @default.
- W3146025091 hasOpenAccess W3146025091 @default.
- W3146025091 hasPrimaryLocation W31460250911 @default.
- W3146025091 hasRelatedWork W112744582 @default.
- W3146025091 hasRelatedWork W1485630101 @default.
- W3146025091 hasRelatedWork W1596426534 @default.
- W3146025091 hasRelatedWork W172869079 @default.
- W3146025091 hasRelatedWork W2275988210 @default.
- W3146025091 hasRelatedWork W2356875448 @default.
- W3146025091 hasRelatedWork W2361412785 @default.
- W3146025091 hasRelatedWork W2385621972 @default.
- W3146025091 hasRelatedWork W2498017833 @default.
- W3146025091 hasRelatedWork W3040872486 @default.
- W3146025091 isParatext "false" @default.
- W3146025091 isRetracted "false" @default.
- W3146025091 magId "3146025091" @default.
- W3146025091 workType "article" @default.