Matches in SemOpenAlex for { <https://semopenalex.org/work/W2891648438> ?p ?o ?g. }
Showing items 1 to 77 of
77
with 100 items per page.
- W2891648438 abstract "Human pose estimation is an essential yet challenging task in computer vision. One of the reasons for this difficulty is that there are many redundant regions in the images. In this work, we proposed a convolutional network architecture combined with the novel attention model. We named it attention convolutional neural network (ACNN). ACNN learns to focus on specific regions of different input features. It's a multi-stage architecture. Early stages filtrate the nothing-regions, such as background and redundant body parts. And then, they submit the important regions which contain the joints of the human body to the following stages to get a more accurate result. What's more, it does not require extra manual annotations and self-learning is one of our intentions. We separately trained the network because the attention learning task and the pose estimation task are not independent. State-of-the-art performance is obtained on the MPII benchmarks." @default.
- W2891648438 created "2018-09-27" @default.
- W2891648438 creator A5049558861 @default.
- W2891648438 creator A5054816040 @default.
- W2891648438 creator A5088027106 @default.
- W2891648438 date "2018-09-22" @default.
- W2891648438 modified "2023-09-27" @default.
- W2891648438 title "Focus On What's Important: Self-Attention Model for Human Pose Estimation" @default.
- W2891648438 hasPublicationYear "2018" @default.
- W2891648438 type Work @default.
- W2891648438 sameAs 2891648438 @default.
- W2891648438 citedByCount "0" @default.
- W2891648438 crossrefType "posted-content" @default.
- W2891648438 hasAuthorship W2891648438A5049558861 @default.
- W2891648438 hasAuthorship W2891648438A5054816040 @default.
- W2891648438 hasAuthorship W2891648438A5088027106 @default.
- W2891648438 hasConcept C108583219 @default.
- W2891648438 hasConcept C119857082 @default.
- W2891648438 hasConcept C120665830 @default.
- W2891648438 hasConcept C121332964 @default.
- W2891648438 hasConcept C123657996 @default.
- W2891648438 hasConcept C127413603 @default.
- W2891648438 hasConcept C142362112 @default.
- W2891648438 hasConcept C153180895 @default.
- W2891648438 hasConcept C153349607 @default.
- W2891648438 hasConcept C154945302 @default.
- W2891648438 hasConcept C192209626 @default.
- W2891648438 hasConcept C201995342 @default.
- W2891648438 hasConcept C2780451532 @default.
- W2891648438 hasConcept C41008148 @default.
- W2891648438 hasConcept C52102323 @default.
- W2891648438 hasConcept C81363708 @default.
- W2891648438 hasConcept C96250715 @default.
- W2891648438 hasConceptScore W2891648438C108583219 @default.
- W2891648438 hasConceptScore W2891648438C119857082 @default.
- W2891648438 hasConceptScore W2891648438C120665830 @default.
- W2891648438 hasConceptScore W2891648438C121332964 @default.
- W2891648438 hasConceptScore W2891648438C123657996 @default.
- W2891648438 hasConceptScore W2891648438C127413603 @default.
- W2891648438 hasConceptScore W2891648438C142362112 @default.
- W2891648438 hasConceptScore W2891648438C153180895 @default.
- W2891648438 hasConceptScore W2891648438C153349607 @default.
- W2891648438 hasConceptScore W2891648438C154945302 @default.
- W2891648438 hasConceptScore W2891648438C192209626 @default.
- W2891648438 hasConceptScore W2891648438C201995342 @default.
- W2891648438 hasConceptScore W2891648438C2780451532 @default.
- W2891648438 hasConceptScore W2891648438C41008148 @default.
- W2891648438 hasConceptScore W2891648438C52102323 @default.
- W2891648438 hasConceptScore W2891648438C81363708 @default.
- W2891648438 hasConceptScore W2891648438C96250715 @default.
- W2891648438 hasLocation W28916484381 @default.
- W2891648438 hasOpenAccess W2891648438 @default.
- W2891648438 hasPrimaryLocation W28916484381 @default.
- W2891648438 hasRelatedWork W102025090 @default.
- W2891648438 hasRelatedWork W1932321571 @default.
- W2891648438 hasRelatedWork W2222082930 @default.
- W2891648438 hasRelatedWork W2726347837 @default.
- W2891648438 hasRelatedWork W2794475071 @default.
- W2891648438 hasRelatedWork W2886356788 @default.
- W2891648438 hasRelatedWork W2891048484 @default.
- W2891648438 hasRelatedWork W2921496992 @default.
- W2891648438 hasRelatedWork W2952504680 @default.
- W2891648438 hasRelatedWork W2958088908 @default.
- W2891648438 hasRelatedWork W3006714671 @default.
- W2891648438 hasRelatedWork W3032128600 @default.
- W2891648438 hasRelatedWork W3035637226 @default.
- W2891648438 hasRelatedWork W3081127035 @default.
- W2891648438 hasRelatedWork W3090086814 @default.
- W2891648438 hasRelatedWork W3120797281 @default.
- W2891648438 hasRelatedWork W3129279281 @default.
- W2891648438 hasRelatedWork W3138282301 @default.
- W2891648438 hasRelatedWork W3170144722 @default.
- W2891648438 hasRelatedWork W3204366333 @default.
- W2891648438 isParatext "false" @default.
- W2891648438 isRetracted "false" @default.
- W2891648438 magId "2891648438" @default.
- W2891648438 workType "article" @default.