Matches in SemOpenAlex for { <https://semopenalex.org/work/W2964209782> ?p ?o ?g. }
Showing items 1 to 100 of
100
with 100 items per page.
- W2964209782 abstract "We propose a network for Congested Scene Recognition called CSRNet to provide a data-driven and deep learning method that can understand highly congested scenes and perform accurate count estimation as well as present high-quality density maps. The proposed CSRNet is composed of two major components: a convolutional neural network (CNN) as the front-end for 2D feature extraction and a dilated CNN for the back-end, which uses dilated kernels to deliver larger reception fields and to replace pooling operations. CSRNet is an easy-trained model because of its pure convolutional structure. We demonstrate CSRNet on four datasets (ShanghaiTech dataset, the UCF_CC_50 dataset, the WorldEXPO'10 dataset, and the UCSD dataset) and we deliver the state-of-the-art performance. In the ShanghaiTech Part_B dataset, CSRNet achieves 47.3% lower Mean Absolute Error (MAE) than the previous state-of-the-art method. We extend the targeted applications for counting other objects, such as the vehicle in TRANCOS dataset. Results show that CSRNet significantly improves the output quality with 15.4% lower MAE than the previous state-of-the-art approach." @default.
- W2964209782 created "2019-07-30" @default.
- W2964209782 creator A5008678513 @default.
- W2964209782 creator A5015184109 @default.
- W2964209782 creator A5056321228 @default.
- W2964209782 date "2018-06-01" @default.
- W2964209782 modified "2023-10-16" @default.
- W2964209782 title "CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenes" @default.
- W2964209782 cites W1745334888 @default.
- W2964209782 cites W1903029394 @default.
- W2964209782 cites W1910776219 @default.
- W2964209782 cites W2031454541 @default.
- W2964209782 cites W2065994824 @default.
- W2964209782 cites W2072232009 @default.
- W2964209782 cites W2075875861 @default.
- W2964209782 cites W2079023123 @default.
- W2964209782 cites W2123175289 @default.
- W2964209782 cites W2124386111 @default.
- W2964209782 cites W2133515615 @default.
- W2964209782 cites W2133665775 @default.
- W2964209782 cites W2155893237 @default.
- W2964209782 cites W2168356304 @default.
- W2964209782 cites W2207893099 @default.
- W2964209782 cites W2276486856 @default.
- W2964209782 cites W2288514685 @default.
- W2964209782 cites W2293078015 @default.
- W2964209782 cites W2321408197 @default.
- W2964209782 cites W2431931973 @default.
- W2964209782 cites W2463631526 @default.
- W2964209782 cites W2514654788 @default.
- W2964209782 cites W2517615595 @default.
- W2964209782 cites W2531409750 @default.
- W2964209782 cites W2541389513 @default.
- W2964209782 cites W2600144439 @default.
- W2964209782 cites W2741077351 @default.
- W2964209782 cites W2762910930 @default.
- W2964209782 cites W2962720716 @default.
- W2964209782 cites W2962854645 @default.
- W2964209782 cites W2963035940 @default.
- W2964209782 cites W3097096317 @default.
- W2964209782 cites W4236408538 @default.
- W2964209782 cites W815611303 @default.
- W2964209782 doi "https://doi.org/10.1109/cvpr.2018.00120" @default.
- W2964209782 hasPublicationYear "2018" @default.
- W2964209782 type Work @default.
- W2964209782 sameAs 2964209782 @default.
- W2964209782 citedByCount "787" @default.
- W2964209782 countsByYear W29642097822018 @default.
- W2964209782 countsByYear W29642097822019 @default.
- W2964209782 countsByYear W29642097822020 @default.
- W2964209782 countsByYear W29642097822021 @default.
- W2964209782 countsByYear W29642097822022 @default.
- W2964209782 countsByYear W29642097822023 @default.
- W2964209782 crossrefType "proceedings-article" @default.
- W2964209782 hasAuthorship W2964209782A5008678513 @default.
- W2964209782 hasAuthorship W2964209782A5015184109 @default.
- W2964209782 hasAuthorship W2964209782A5056321228 @default.
- W2964209782 hasBestOaLocation W29642097822 @default.
- W2964209782 hasConcept C108583219 @default.
- W2964209782 hasConcept C11413529 @default.
- W2964209782 hasConcept C138885662 @default.
- W2964209782 hasConcept C153180895 @default.
- W2964209782 hasConcept C154945302 @default.
- W2964209782 hasConcept C2776401178 @default.
- W2964209782 hasConcept C41008148 @default.
- W2964209782 hasConcept C41895202 @default.
- W2964209782 hasConcept C48103436 @default.
- W2964209782 hasConcept C52622490 @default.
- W2964209782 hasConcept C70437156 @default.
- W2964209782 hasConcept C81363708 @default.
- W2964209782 hasConceptScore W2964209782C108583219 @default.
- W2964209782 hasConceptScore W2964209782C11413529 @default.
- W2964209782 hasConceptScore W2964209782C138885662 @default.
- W2964209782 hasConceptScore W2964209782C153180895 @default.
- W2964209782 hasConceptScore W2964209782C154945302 @default.
- W2964209782 hasConceptScore W2964209782C2776401178 @default.
- W2964209782 hasConceptScore W2964209782C41008148 @default.
- W2964209782 hasConceptScore W2964209782C41895202 @default.
- W2964209782 hasConceptScore W2964209782C48103436 @default.
- W2964209782 hasConceptScore W2964209782C52622490 @default.
- W2964209782 hasConceptScore W2964209782C70437156 @default.
- W2964209782 hasConceptScore W2964209782C81363708 @default.
- W2964209782 hasLocation W29642097821 @default.
- W2964209782 hasLocation W29642097822 @default.
- W2964209782 hasOpenAccess W2964209782 @default.
- W2964209782 hasPrimaryLocation W29642097821 @default.
- W2964209782 hasRelatedWork W2626256601 @default.
- W2964209782 hasRelatedWork W2810679507 @default.
- W2964209782 hasRelatedWork W2900413183 @default.
- W2964209782 hasRelatedWork W2953234277 @default.
- W2964209782 hasRelatedWork W3029198973 @default.
- W2964209782 hasRelatedWork W3133861977 @default.
- W2964209782 hasRelatedWork W3167935049 @default.
- W2964209782 hasRelatedWork W3193565141 @default.
- W2964209782 hasRelatedWork W4226493464 @default.
- W2964209782 hasRelatedWork W4312417841 @default.
- W2964209782 isParatext "false" @default.
- W2964209782 isRetracted "false" @default.
- W2964209782 magId "2964209782" @default.
- W2964209782 workType "article" @default.