Matches in SemOpenAlex for { <https://semopenalex.org/work/W3042870837> ?p ?o ?g. }
- W3042870837 endingPage "103777" @default.
- W3042870837 startingPage "103777" @default.
- W3042870837 abstract "This research develops a cross-scale convolutional spatial generative adversarial network (CSGAN), in order to estimate the crowd density from images accurately. It consists of two similar generators, one for the whole feature extraction, and the other for patch scale feature extraction. An encoder–decoder structure is employed to generate density maps from input images or patches. Additionally, a new objective function for crowd counting called cross-scale consistency pursuit containing an adversarial loss, L2 loss, perceptual loss, and consistency loss, is developed to make the generated density maps more realistic and closer to the ground truth. The effectiveness of the proposed CSGAN is verified in two public datasets. Results indicate that the new objective function is able to reach the most satisfying value of evaluation metrics in both the low-density and high-density crowd scenes when it is compared with other state-of-the-art methods on the test datasets. Moreover, the proposed CSGAN is more practical and flexible due to the smaller computational complexity. Its estimation capability will be significantly improved even in a small size of training data. Overall, this research contributes to the development of a novel computer vision approach together with a new objective function to generate density maps from cross-scale crowd images, enabling the counting process more accurately and efficiently." @default.
- W3042870837 created "2020-07-23" @default.
- W3042870837 creator A5056869509 @default.
- W3042870837 creator A5062330704 @default.
- W3042870837 creator A5063481799 @default.
- W3042870837 creator A5067890765 @default.
- W3042870837 date "2020-09-01" @default.
- W3042870837 modified "2023-10-02" @default.
- W3042870837 title "Cross-scale generative adversarial network for crowd density estimation from images" @default.
- W3042870837 cites W1904463290 @default.
- W3042870837 cites W1962468782 @default.
- W3042870837 cites W1976959044 @default.
- W3042870837 cites W1992825118 @default.
- W3042870837 cites W2036536917 @default.
- W3042870837 cites W2042015300 @default.
- W3042870837 cites W2053045874 @default.
- W3042870837 cites W2058907003 @default.
- W3042870837 cites W2066099897 @default.
- W3042870837 cites W2068627809 @default.
- W3042870837 cites W2072232009 @default.
- W3042870837 cites W2075875861 @default.
- W3042870837 cites W2088929512 @default.
- W3042870837 cites W2096246546 @default.
- W3042870837 cites W2118704323 @default.
- W3042870837 cites W2125337786 @default.
- W3042870837 cites W2130751540 @default.
- W3042870837 cites W2138890315 @default.
- W3042870837 cites W2138948290 @default.
- W3042870837 cites W2165368973 @default.
- W3042870837 cites W2197234429 @default.
- W3042870837 cites W2207893099 @default.
- W3042870837 cites W2208880054 @default.
- W3042870837 cites W2343797329 @default.
- W3042870837 cites W2463631526 @default.
- W3042870837 cites W2473415337 @default.
- W3042870837 cites W2481453975 @default.
- W3042870837 cites W2517866598 @default.
- W3042870837 cites W2639936844 @default.
- W3042870837 cites W2766504181 @default.
- W3042870837 cites W2773334424 @default.
- W3042870837 cites W2801961186 @default.
- W3042870837 cites W2803309154 @default.
- W3042870837 cites W2905898036 @default.
- W3042870837 cites W2938620257 @default.
- W3042870837 cites W2944330663 @default.
- W3042870837 cites W2963035940 @default.
- W3042870837 cites W2963073614 @default.
- W3042870837 cites W2963091558 @default.
- W3042870837 cites W2963838390 @default.
- W3042870837 cites W3007999534 @default.
- W3042870837 cites W3013298624 @default.
- W3042870837 cites W3122238731 @default.
- W3042870837 doi "https://doi.org/10.1016/j.engappai.2020.103777" @default.
- W3042870837 hasPublicationYear "2020" @default.
- W3042870837 type Work @default.
- W3042870837 sameAs 3042870837 @default.
- W3042870837 citedByCount "15" @default.
- W3042870837 countsByYear W30428708372020 @default.
- W3042870837 countsByYear W30428708372021 @default.
- W3042870837 countsByYear W30428708372022 @default.
- W3042870837 countsByYear W30428708372023 @default.
- W3042870837 crossrefType "journal-article" @default.
- W3042870837 hasAuthorship W3042870837A5056869509 @default.
- W3042870837 hasAuthorship W3042870837A5062330704 @default.
- W3042870837 hasAuthorship W3042870837A5063481799 @default.
- W3042870837 hasAuthorship W3042870837A5067890765 @default.
- W3042870837 hasConcept C105795698 @default.
- W3042870837 hasConcept C111919701 @default.
- W3042870837 hasConcept C118505674 @default.
- W3042870837 hasConcept C121332964 @default.
- W3042870837 hasConcept C138885662 @default.
- W3042870837 hasConcept C14036430 @default.
- W3042870837 hasConcept C146849305 @default.
- W3042870837 hasConcept C153180895 @default.
- W3042870837 hasConcept C154945302 @default.
- W3042870837 hasConcept C185429906 @default.
- W3042870837 hasConcept C189508267 @default.
- W3042870837 hasConcept C2776401178 @default.
- W3042870837 hasConcept C2776436953 @default.
- W3042870837 hasConcept C2778755073 @default.
- W3042870837 hasConcept C33923547 @default.
- W3042870837 hasConcept C37736160 @default.
- W3042870837 hasConcept C39890363 @default.
- W3042870837 hasConcept C41008148 @default.
- W3042870837 hasConcept C41895202 @default.
- W3042870837 hasConcept C62520636 @default.
- W3042870837 hasConcept C78458016 @default.
- W3042870837 hasConcept C81363708 @default.
- W3042870837 hasConcept C86803240 @default.
- W3042870837 hasConceptScore W3042870837C105795698 @default.
- W3042870837 hasConceptScore W3042870837C111919701 @default.
- W3042870837 hasConceptScore W3042870837C118505674 @default.
- W3042870837 hasConceptScore W3042870837C121332964 @default.
- W3042870837 hasConceptScore W3042870837C138885662 @default.
- W3042870837 hasConceptScore W3042870837C14036430 @default.
- W3042870837 hasConceptScore W3042870837C146849305 @default.
- W3042870837 hasConceptScore W3042870837C153180895 @default.
- W3042870837 hasConceptScore W3042870837C154945302 @default.