Matches in SemOpenAlex for { <https://semopenalex.org/work/W4379116441> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W4379116441 abstract "Accurate pose estimation is crucial for understanding human behavior in images or videos. Given an RGB image, we want to be able to accurately locate some important keypoints on the body. Understanding human pose and body structure is important for high-level tasks such as human-computer interaction. Human pose estimation usually has problems such as low discrimination between human body and background, and human pose estimation based on HRnet network does not make full use of important feature information. To solve these problems, a human pose estimation method MCSA-hrnet (Multi-scale Channel and Spatial Attention) based on multi-scale channel and spatial attention is improved by using channel attention mechanism and spatial attention mechanism. Starting from the channel domain and spatial domain, MCSA-HRnet integrates the multi-level attention mechanism into the high-resolution network structure, and designs the channel attention block and spatial attention block. This enables the network to focus on the regions of the image that are highly associated with the human body and not on other regions. MCSA-HRnet uses 1×1 convolutions for information extraction in the core part of the ca block (channel attention block) and parallel <tex xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>$boldsymbol{3mathrm{x}3}$</tex> and <tex xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>$boldsymbol{5mathrm{x}5}$</tex> convolutions in the sa block (spatial attention block). Different sizes of parallel convolutions can derive spatial attention maps of different scales, which makes the ability of the network to distinguish human features from background features more significant. Thus, the human body region and its key points can be accurately located. The improved method is verified on COCO keypoint dataset, and the results show that MCSA-HRnet can effectively improve the accuracy of human pose estimation joint point localization." @default.
- W4379116441 created "2023-06-03" @default.
- W4379116441 creator A5019258016 @default.
- W4379116441 date "2023-01-06" @default.
- W4379116441 modified "2023-09-23" @default.
- W4379116441 title "Study on human pose estimation based on channel and spatial attention" @default.
- W4379116441 cites W2307770531 @default.
- W4379116441 cites W2559085405 @default.
- W4379116441 cites W2752782242 @default.
- W4379116441 cites W2963150697 @default.
- W4379116441 cites W2963402313 @default.
- W4379116441 cites W2964221239 @default.
- W4379116441 cites W2964304707 @default.
- W4379116441 cites W2969825018 @default.
- W4379116441 cites W3014641072 @default.
- W4379116441 cites W3034399482 @default.
- W4379116441 cites W3171398643 @default.
- W4379116441 doi "https://doi.org/10.1109/iccece58074.2023.10135500" @default.
- W4379116441 hasPublicationYear "2023" @default.
- W4379116441 type Work @default.
- W4379116441 citedByCount "0" @default.
- W4379116441 crossrefType "proceedings-article" @default.
- W4379116441 hasAuthorship W4379116441A5019258016 @default.
- W4379116441 hasConcept C105795698 @default.
- W4379116441 hasConcept C115961682 @default.
- W4379116441 hasConcept C127162648 @default.
- W4379116441 hasConcept C134306372 @default.
- W4379116441 hasConcept C138885662 @default.
- W4379116441 hasConcept C153180895 @default.
- W4379116441 hasConcept C154945302 @default.
- W4379116441 hasConcept C159620131 @default.
- W4379116441 hasConcept C205649164 @default.
- W4379116441 hasConcept C2524010 @default.
- W4379116441 hasConcept C2776401178 @default.
- W4379116441 hasConcept C2777210771 @default.
- W4379116441 hasConcept C2778755073 @default.
- W4379116441 hasConcept C31258907 @default.
- W4379116441 hasConcept C31972630 @default.
- W4379116441 hasConcept C33923547 @default.
- W4379116441 hasConcept C36503486 @default.
- W4379116441 hasConcept C41008148 @default.
- W4379116441 hasConcept C41895202 @default.
- W4379116441 hasConcept C52102323 @default.
- W4379116441 hasConcept C58640448 @default.
- W4379116441 hasConcept C82990744 @default.
- W4379116441 hasConceptScore W4379116441C105795698 @default.
- W4379116441 hasConceptScore W4379116441C115961682 @default.
- W4379116441 hasConceptScore W4379116441C127162648 @default.
- W4379116441 hasConceptScore W4379116441C134306372 @default.
- W4379116441 hasConceptScore W4379116441C138885662 @default.
- W4379116441 hasConceptScore W4379116441C153180895 @default.
- W4379116441 hasConceptScore W4379116441C154945302 @default.
- W4379116441 hasConceptScore W4379116441C159620131 @default.
- W4379116441 hasConceptScore W4379116441C205649164 @default.
- W4379116441 hasConceptScore W4379116441C2524010 @default.
- W4379116441 hasConceptScore W4379116441C2776401178 @default.
- W4379116441 hasConceptScore W4379116441C2777210771 @default.
- W4379116441 hasConceptScore W4379116441C2778755073 @default.
- W4379116441 hasConceptScore W4379116441C31258907 @default.
- W4379116441 hasConceptScore W4379116441C31972630 @default.
- W4379116441 hasConceptScore W4379116441C33923547 @default.
- W4379116441 hasConceptScore W4379116441C36503486 @default.
- W4379116441 hasConceptScore W4379116441C41008148 @default.
- W4379116441 hasConceptScore W4379116441C41895202 @default.
- W4379116441 hasConceptScore W4379116441C52102323 @default.
- W4379116441 hasConceptScore W4379116441C58640448 @default.
- W4379116441 hasConceptScore W4379116441C82990744 @default.
- W4379116441 hasLocation W43791164411 @default.
- W4379116441 hasOpenAccess W4379116441 @default.
- W4379116441 hasPrimaryLocation W43791164411 @default.
- W4379116441 hasRelatedWork W2544359817 @default.
- W4379116441 hasRelatedWork W2794187083 @default.
- W4379116441 hasRelatedWork W2822883015 @default.
- W4379116441 hasRelatedWork W2891001608 @default.
- W4379116441 hasRelatedWork W2972219788 @default.
- W4379116441 hasRelatedWork W2997897143 @default.
- W4379116441 hasRelatedWork W3102636071 @default.
- W4379116441 hasRelatedWork W3115178140 @default.
- W4379116441 hasRelatedWork W4313046826 @default.
- W4379116441 hasRelatedWork W4320809347 @default.
- W4379116441 isParatext "false" @default.
- W4379116441 isRetracted "false" @default.
- W4379116441 workType "article" @default.