Matches in SemOpenAlex for { <https://semopenalex.org/work/W3136074530> ?p ?o ?g. }
- W3136074530 abstract "Crowd counting is a task worth exploring in modern society because of its wide applications such as public safety and video monitoring. Many CNN-based approaches have been proposed to improve the accuracy of estimation, but there are some inherent issues affect the performance, such as overfitting and details lost caused by pooling layers. To tackle these problems, in this paper, we propose an effective network called MDSNet, which introduces a novel supervision framework called Multi-channel Deep Supervision (MDS). The MDS conducts channel-wise supervision on the decoder of the estimation model to help generate the density maps. To obtain the accurate supervision information of different channels, the MDSNet employs an auxiliary network called SupervisionNet (SN) to generate abundant supervision maps based on existing groundtruth. Besides the traditional density map supervision, we also use the SN to convert the dot annotations into continuous supervision information and conduct dot supervision in the MDSNet. Extensive experiments on several mainstream benchmarks show that the proposed MDSNet achieves competitive results and the MDS significantly improves the performance without changing the network structure." @default.
- W3136074530 created "2021-03-29" @default.
- W3136074530 creator A5015195367 @default.
- W3136074530 creator A5068918243 @default.
- W3136074530 creator A5083707253 @default.
- W3136074530 creator A5087975803 @default.
- W3136074530 date "2021-03-17" @default.
- W3136074530 modified "2023-09-27" @default.
- W3136074530 title "Multi-channel Deep Supervision for Crowd Counting." @default.
- W3136074530 cites W1531249942 @default.
- W3136074530 cites W1686810756 @default.
- W3136074530 cites W1910776219 @default.
- W3136074530 cites W1976959044 @default.
- W3136074530 cites W1978232622 @default.
- W3136074530 cites W2097117768 @default.
- W3136074530 cites W2097324787 @default.
- W3136074530 cites W2122190623 @default.
- W3136074530 cites W2123175289 @default.
- W3136074530 cites W2135347708 @default.
- W3136074530 cites W2145983039 @default.
- W3136074530 cites W2161969291 @default.
- W3136074530 cites W2163352848 @default.
- W3136074530 cites W2463631526 @default.
- W3136074530 cites W2474152637 @default.
- W3136074530 cites W2517615595 @default.
- W3136074530 cites W2519281173 @default.
- W3136074530 cites W2557106373 @default.
- W3136074530 cites W2560023338 @default.
- W3136074530 cites W2607333215 @default.
- W3136074530 cites W2729018917 @default.
- W3136074530 cites W2740101263 @default.
- W3136074530 cites W2741077351 @default.
- W3136074530 cites W2745597836 @default.
- W3136074530 cites W2769924742 @default.
- W3136074530 cites W2798490576 @default.
- W3136074530 cites W2798781811 @default.
- W3136074530 cites W2808519136 @default.
- W3136074530 cites W2895051362 @default.
- W3136074530 cites W2903922555 @default.
- W3136074530 cites W2913401361 @default.
- W3136074530 cites W2919958344 @default.
- W3136074530 cites W2945574898 @default.
- W3136074530 cites W2950565945 @default.
- W3136074530 cites W2962720716 @default.
- W3136074530 cites W2962870549 @default.
- W3136074530 cites W2963035940 @default.
- W3136074530 cites W2963231953 @default.
- W3136074530 cites W2963396070 @default.
- W3136074530 cites W2963693541 @default.
- W3136074530 cites W2964057995 @default.
- W3136074530 cites W2964203052 @default.
- W3136074530 cites W2964209782 @default.
- W3136074530 cites W2967069910 @default.
- W3136074530 cites W2969620138 @default.
- W3136074530 cites W2982130202 @default.
- W3136074530 cites W2997403460 @default.
- W3136074530 cites W2997996590 @default.
- W3136074530 cites W3004672782 @default.
- W3136074530 cites W3027606690 @default.
- W3136074530 cites W3082125592 @default.
- W3136074530 cites W3108659450 @default.
- W3136074530 hasPublicationYear "2021" @default.
- W3136074530 type Work @default.
- W3136074530 sameAs 3136074530 @default.
- W3136074530 citedByCount "1" @default.
- W3136074530 countsByYear W31360745302021 @default.
- W3136074530 crossrefType "posted-content" @default.
- W3136074530 hasAuthorship W3136074530A5015195367 @default.
- W3136074530 hasAuthorship W3136074530A5068918243 @default.
- W3136074530 hasAuthorship W3136074530A5083707253 @default.
- W3136074530 hasAuthorship W3136074530A5087975803 @default.
- W3136074530 hasConcept C108583219 @default.
- W3136074530 hasConcept C119857082 @default.
- W3136074530 hasConcept C124101348 @default.
- W3136074530 hasConcept C127162648 @default.
- W3136074530 hasConcept C154945302 @default.
- W3136074530 hasConcept C162324750 @default.
- W3136074530 hasConcept C187736073 @default.
- W3136074530 hasConcept C22019652 @default.
- W3136074530 hasConcept C2780451532 @default.
- W3136074530 hasConcept C31258907 @default.
- W3136074530 hasConcept C41008148 @default.
- W3136074530 hasConcept C50644808 @default.
- W3136074530 hasConcept C70437156 @default.
- W3136074530 hasConceptScore W3136074530C108583219 @default.
- W3136074530 hasConceptScore W3136074530C119857082 @default.
- W3136074530 hasConceptScore W3136074530C124101348 @default.
- W3136074530 hasConceptScore W3136074530C127162648 @default.
- W3136074530 hasConceptScore W3136074530C154945302 @default.
- W3136074530 hasConceptScore W3136074530C162324750 @default.
- W3136074530 hasConceptScore W3136074530C187736073 @default.
- W3136074530 hasConceptScore W3136074530C22019652 @default.
- W3136074530 hasConceptScore W3136074530C2780451532 @default.
- W3136074530 hasConceptScore W3136074530C31258907 @default.
- W3136074530 hasConceptScore W3136074530C41008148 @default.
- W3136074530 hasConceptScore W3136074530C50644808 @default.
- W3136074530 hasConceptScore W3136074530C70437156 @default.
- W3136074530 hasLocation W31360745301 @default.
- W3136074530 hasOpenAccess W3136074530 @default.
- W3136074530 hasPrimaryLocation W31360745301 @default.