FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3120552785> ?p ?o ?g. }

• W3120552785 abstract "Given a target pose, how to generate an image of a specific style with that target pose remains an ill-posed and thus complicated problem. Most recent works treat the human pose synthesis tasks as an image spatial transformation problem using flow warping techniques. However, we observe that, due to the inherent ill-posed nature of many complicated human poses, former methods fail to generate body parts. To tackle this problem, we propose a feature-level flow attention module and an Enhancer Network. The flow attention module produces a flow attention mask to guide the combination of the flow-warped features and the structural pose features. Then, we apply the Enhancer Network to re-fine the coarse image by injecting the pose information. We present our experimental evaluation both qualitatively and quantitatively on DeepFashion, Market-1501, and Youtube dance datasets. Quantitative results show that our method has 12.995 FID at DeepFashion, 25.459 FID at Market-1501, 14.516 FID at Youtube dance datasets, which outperforms some state-of-the-arts including Guide-Pixe2Pixe, Global-Flow-Local-Attn, and CocosNet." @default.
• W3120552785 created "2021-01-18" @default.
• W3120552785 creator A5016846734 @default.
• W3120552785 creator A5059307950 @default.
• W3120552785 creator A5059707268 @default.
• W3120552785 creator A5062200939 @default.
• W3120552785 creator A5064086026 @default.
• W3120552785 creator A5080344490 @default.
• W3120552785 creator A5080799607 @default.
• W3120552785 date "2021-01-01" @default.
• W3120552785 modified "2023-09-25" @default.
• W3120552785 title "Focus and retain: Complement the Broken Pose in Human Image Synthesis" @default.
• W3120552785 cites W2471768434 @default.
• W3120552785 cites W2560474170 @default.
• W3120552785 cites W2585635281 @default.
• W3120552785 cites W2593414223 @default.
• W3120552785 cites W2598591334 @default.
• W3120552785 cites W2603777577 @default.
• W3120552785 cites W2771558241 @default.
• W3120552785 cites W2798429327 @default.
• W3120552785 cites W2962770929 @default.
• W3120552785 cites W2962785568 @default.
• W3120552785 cites W2962793481 @default.
• W3120552785 cites W2962974533 @default.
• W3120552785 cites W2963091558 @default.
• W3120552785 cites W2963266880 @default.
• W3120552785 cites W2963268050 @default.
• W3120552785 cites W2963626105 @default.
• W3120552785 cites W2963734522 @default.
• W3120552785 cites W2963781481 @default.
• W3120552785 cites W2963891416 @default.
• W3120552785 cites W2964002510 @default.
• W3120552785 cites W2964094136 @default.
• W3120552785 cites W2964186374 @default.
• W3120552785 cites W2981682056 @default.
• W3120552785 cites W2981950698 @default.
• W3120552785 cites W2982413914 @default.
• W3120552785 cites W2982697283 @default.
• W3120552785 cites W2984983779 @default.
• W3120552785 cites W2988021769 @default.
• W3120552785 cites W2991530302 @default.
• W3120552785 cites W3034723751 @default.
• W3120552785 cites W3034950620 @default.
• W3120552785 cites W764651262 @default.
• W3120552785 doi "https://doi.org/10.1109/wacv48630.2021.00341" @default.
• W3120552785 hasPublicationYear "2021" @default.
• W3120552785 type Work @default.
• W3120552785 sameAs 3120552785 @default.
• W3120552785 citedByCount "0" @default.
• W3120552785 crossrefType "proceedings-article" @default.
• W3120552785 hasAuthorship W3120552785A5016846734 @default.
• W3120552785 hasAuthorship W3120552785A5059307950 @default.
• W3120552785 hasAuthorship W3120552785A5059707268 @default.
• W3120552785 hasAuthorship W3120552785A5062200939 @default.
• W3120552785 hasAuthorship W3120552785A5064086026 @default.
• W3120552785 hasAuthorship W3120552785A5080344490 @default.
• W3120552785 hasAuthorship W3120552785A5080799607 @default.
• W3120552785 hasConcept C104317684 @default.
• W3120552785 hasConcept C112313634 @default.
• W3120552785 hasConcept C11413529 @default.
• W3120552785 hasConcept C115961682 @default.
• W3120552785 hasConcept C120665830 @default.
• W3120552785 hasConcept C121332964 @default.
• W3120552785 hasConcept C127716648 @default.
• W3120552785 hasConcept C138885662 @default.
• W3120552785 hasConcept C154945302 @default.
• W3120552785 hasConcept C155542232 @default.
• W3120552785 hasConcept C157202957 @default.
• W3120552785 hasConcept C185592680 @default.
• W3120552785 hasConcept C188082640 @default.
• W3120552785 hasConcept C192209626 @default.
• W3120552785 hasConcept C2524010 @default.
• W3120552785 hasConcept C2776401178 @default.
• W3120552785 hasConcept C31972630 @default.
• W3120552785 hasConcept C33923547 @default.
• W3120552785 hasConcept C38349280 @default.
• W3120552785 hasConcept C41008148 @default.
• W3120552785 hasConcept C41895202 @default.
• W3120552785 hasConcept C52102323 @default.
• W3120552785 hasConcept C52622490 @default.
• W3120552785 hasConcept C55439883 @default.
• W3120552785 hasConcept C55493867 @default.
• W3120552785 hasConceptScore W3120552785C104317684 @default.
• W3120552785 hasConceptScore W3120552785C112313634 @default.
• W3120552785 hasConceptScore W3120552785C11413529 @default.
• W3120552785 hasConceptScore W3120552785C115961682 @default.
• W3120552785 hasConceptScore W3120552785C120665830 @default.
• W3120552785 hasConceptScore W3120552785C121332964 @default.
• W3120552785 hasConceptScore W3120552785C127716648 @default.
• W3120552785 hasConceptScore W3120552785C138885662 @default.
• W3120552785 hasConceptScore W3120552785C154945302 @default.
• W3120552785 hasConceptScore W3120552785C155542232 @default.
• W3120552785 hasConceptScore W3120552785C157202957 @default.
• W3120552785 hasConceptScore W3120552785C185592680 @default.
• W3120552785 hasConceptScore W3120552785C188082640 @default.
• W3120552785 hasConceptScore W3120552785C192209626 @default.
• W3120552785 hasConceptScore W3120552785C2524010 @default.
• W3120552785 hasConceptScore W3120552785C2776401178 @default.
• W3120552785 hasConceptScore W3120552785C31972630 @default.
• W3120552785 hasConceptScore W3120552785C33923547 @default.

• next