FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2967161970> ?p ?o ?g. }

• W2967161970 abstract "In crowd counting datasets, each person is annotated by a point, which is usually the center of the head. And the task is to estimate the total count in a crowd scene. Most of the state-of-the-art methods are based on density map estimation, which convert the sparse point annotations into a ground truth density map through a Gaussian kernel, and then use it as the learning target to train a density map estimator. However, such a ground-truth density map is imperfect due to occlusions, perspective effects, variations in object shapes, etc. On the contrary, we propose emph{Bayesian loss}, a novel loss function which constructs a density contribution probability model from the point annotations. Instead of constraining the value at every pixel in the density map, the proposed training loss adopts a more reliable supervision on the count expectation at each annotated point. Without bells and whistles, the loss function makes substantial improvements over the baseline loss on all tested datasets. Moreover, our proposed loss function equipped with a standard backbone network, without using any external detectors or multi-scale architectures, plays favourably against the state of the arts. Our method outperforms previous best approaches by a large margin on the latest and largest UCF-QNRF dataset. The source code is available at url{https://github.com/ZhihengCV/Baysian-Crowd-Counting}." @default.
• W2967161970 created "2019-08-22" @default.
• W2967161970 creator A5008366979 @default.
• W2967161970 creator A5026880795 @default.
• W2967161970 creator A5040886197 @default.
• W2967161970 creator A5043039309 @default.
• W2967161970 date "2019-08-10" @default.
• W2967161970 modified "2023-09-30" @default.
• W2967161970 title "Bayesian Loss for Crowd Count Estimation with Point Supervision" @default.
• W2967161970 cites W1542079534 @default.
• W2967161970 cites W1677182931 @default.
• W2967161970 cites W1908321067 @default.
• W2967161970 cites W1910776219 @default.
• W2967161970 cites W1978232622 @default.
• W2967161970 cites W2027922120 @default.
• W2967161970 cites W2072232009 @default.
• W2967161970 cites W2075875861 @default.
• W2967161970 cites W2101178587 @default.
• W2967161970 cites W2120419212 @default.
• W2967161970 cites W2120815373 @default.
• W2967161970 cites W2122243179 @default.
• W2967161970 cites W2123175289 @default.
• W2967161970 cites W2145983039 @default.
• W2967161970 cites W2151666244 @default.
• W2967161970 cites W2155916750 @default.
• W2967161970 cites W2162915993 @default.
• W2967161970 cites W2163605009 @default.
• W2967161970 cites W2197234429 @default.
• W2967161970 cites W2207893099 @default.
• W2967161970 cites W2312404985 @default.
• W2967161970 cites W2463631526 @default.
• W2967161970 cites W2514654788 @default.
• W2967161970 cites W2519281173 @default.
• W2967161970 cites W2519354012 @default.
• W2967161970 cites W2519786711 @default.
• W2967161970 cites W2520723410 @default.
• W2967161970 cites W2520826941 @default.
• W2967161970 cites W2613718673 @default.
• W2967161970 cites W2738760914 @default.
• W2967161970 cites W2741077351 @default.
• W2967161970 cites W2798314446 @default.
• W2967161970 cites W2798489385 @default.
• W2967161970 cites W2798490576 @default.
• W2967161970 cites W2798618325 @default.
• W2967161970 cites W2798781811 @default.
• W2967161970 cites W2883363148 @default.
• W2967161970 cites W2883929025 @default.
• W2967161970 cites W2884960332 @default.
• W2967161970 cites W2886443245 @default.
• W2967161970 cites W2895051362 @default.
• W2967161970 cites W2895643041 @default.
• W2967161970 cites W2962720716 @default.
• W2967161970 cites W2962835968 @default.
• W2967161970 cites W2962854645 @default.
• W2967161970 cites W2962921175 @default.
• W2967161970 cites W2963035940 @default.
• W2967161970 cites W2963231953 @default.
• W2967161970 cites W2963499661 @default.
• W2967161970 cites W2963681621 @default.
• W2967161970 cites W2963686699 @default.
• W2967161970 cites W2963826106 @default.
• W2967161970 cites W2964018834 @default.
• W2967161970 cites W2964046724 @default.
• W2967161970 cites W2964203052 @default.
• W2967161970 cites W2964264515 @default.
• W2967161970 cites W2964285767 @default.
• W2967161970 cites W2986390834 @default.
• W2967161970 cites W607748843 @default.
• W2967161970 doi "https://doi.org/10.48550/arxiv.1908.03684" @default.
• W2967161970 hasPublicationYear "2019" @default.
• W2967161970 type Work @default.
• W2967161970 sameAs 2967161970 @default.
• W2967161970 citedByCount "6" @default.
• W2967161970 countsByYear W29671619702020 @default.
• W2967161970 countsByYear W29671619702021 @default.
• W2967161970 crossrefType "posted-content" @default.
• W2967161970 hasAuthorship W2967161970A5008366979 @default.
• W2967161970 hasAuthorship W2967161970A5026880795 @default.
• W2967161970 hasAuthorship W2967161970A5040886197 @default.
• W2967161970 hasAuthorship W2967161970A5043039309 @default.
• W2967161970 hasBestOaLocation W29671619701 @default.
• W2967161970 hasConcept C105795698 @default.
• W2967161970 hasConcept C107673813 @default.
• W2967161970 hasConcept C119857082 @default.
• W2967161970 hasConcept C12267149 @default.
• W2967161970 hasConcept C146849305 @default.
• W2967161970 hasConcept C153180895 @default.
• W2967161970 hasConcept C154945302 @default.
• W2967161970 hasConcept C185429906 @default.
• W2967161970 hasConcept C189508267 @default.
• W2967161970 hasConcept C2524010 @default.
• W2967161970 hasConcept C28719098 @default.
• W2967161970 hasConcept C33923547 @default.
• W2967161970 hasConcept C39891107 @default.
• W2967161970 hasConcept C41008148 @default.
• W2967161970 hasConcept C71134354 @default.
• W2967161970 hasConcept C774472 @default.
• W2967161970 hasConceptScore W2967161970C105795698 @default.
• W2967161970 hasConceptScore W2967161970C107673813 @default.
• W2967161970 hasConceptScore W2967161970C119857082 @default.

• next