Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313291290> ?p ?o ?g. }
- W4313291290 endingPage "3382" @default.
- W4313291290 startingPage "3369" @default.
- W4313291290 abstract "The goal of human pose transfer is to transfer the human in the image from the original pose to the desired one. Existing methods utilizing progressive manner have achieved great success. However, they fail to remove background distraction and preserve appearance details in synthesized images since the correlation between the image and pose is not fully exploit. To this end, we propose a novel progressive cross-modal fusion network (PCFN), which consists of multiple cascaded cross-modal fusion blocks (CMFBs). Each CMFB comprises a feature fusion module (FFM) and a cross-modal module (CMM) to take full advantage of appearance and shape information. From an overall perspective, FFM fully exploits the correlation between image features and pose features through the residual gated convolution. Benefitting from feature integration and dynamic selection, CMFB can extract useful information from the image-pose stream. From a local perspective, CMM utilizes the feature-conditioned gated convolution and the pose-guided heterogeneous attention mechanism to update all codes in a crossing manner and enhance the interaction between fusion information and structural information. Qualitative and quantitative experiments demonstrate the superiority of PCFN compared to state-of-the-art methods, which can transfer the correct human features and increase the authenticity of the generated images. At the same time, PCFN can also be applied to supplement the dataset for person re-identification (ReID). PCFN works well for human pose transfer, and our usage of the gated convolution and the attention mechanism also provides references for other conditional generation tasks." @default.
- W4313291290 created "2023-01-06" @default.
- W4313291290 creator A5012772285 @default.
- W4313291290 creator A5038780812 @default.
- W4313291290 creator A5042772858 @default.
- W4313291290 creator A5044936528 @default.
- W4313291290 creator A5049973748 @default.
- W4313291290 date "2023-07-01" @default.
- W4313291290 modified "2023-09-26" @default.
- W4313291290 title "PCFN: Progressive Cross-Modal Fusion Network for Human Pose Transfer" @default.
- W4313291290 cites W2094694112 @default.
- W4313291290 cites W2108598243 @default.
- W4313291290 cites W2112796928 @default.
- W4313291290 cites W2133665775 @default.
- W4313291290 cites W2204750386 @default.
- W4313291290 cites W2331128040 @default.
- W4313291290 cites W2471768434 @default.
- W4313291290 cites W2559085405 @default.
- W4313291290 cites W2771558241 @default.
- W4313291290 cites W2953096069 @default.
- W4313291290 cites W2962793481 @default.
- W4313291290 cites W2962963674 @default.
- W4313291290 cites W2963073614 @default.
- W4313291290 cites W2963266880 @default.
- W4313291290 cites W2963470893 @default.
- W4313291290 cites W2963669520 @default.
- W4313291290 cites W2963734522 @default.
- W4313291290 cites W2963966654 @default.
- W4313291290 cites W2964002510 @default.
- W4313291290 cites W2964024144 @default.
- W4313291290 cites W2964199361 @default.
- W4313291290 cites W2982763192 @default.
- W4313291290 cites W2989505547 @default.
- W4313291290 cites W2991377405 @default.
- W4313291290 cites W2991471181 @default.
- W4313291290 cites W2991530302 @default.
- W4313291290 cites W3010722397 @default.
- W4313291290 cites W3017343282 @default.
- W4313291290 cites W3034509543 @default.
- W4313291290 cites W3034854791 @default.
- W4313291290 cites W3034950620 @default.
- W4313291290 cites W3035515747 @default.
- W4313291290 cites W3106811106 @default.
- W4313291290 cites W3108240585 @default.
- W4313291290 cites W3130957736 @default.
- W4313291290 cites W3135551199 @default.
- W4313291290 cites W3166096919 @default.
- W4313291290 cites W3174133392 @default.
- W4313291290 cites W3214985077 @default.
- W4313291290 cites W4312881655 @default.
- W4313291290 doi "https://doi.org/10.1109/tcsvt.2022.3233060" @default.
- W4313291290 hasPublicationYear "2023" @default.
- W4313291290 type Work @default.
- W4313291290 citedByCount "0" @default.
- W4313291290 crossrefType "journal-article" @default.
- W4313291290 hasAuthorship W4313291290A5012772285 @default.
- W4313291290 hasAuthorship W4313291290A5038780812 @default.
- W4313291290 hasAuthorship W4313291290A5042772858 @default.
- W4313291290 hasAuthorship W4313291290A5044936528 @default.
- W4313291290 hasAuthorship W4313291290A5049973748 @default.
- W4313291290 hasConcept C115961682 @default.
- W4313291290 hasConcept C138885662 @default.
- W4313291290 hasConcept C153180895 @default.
- W4313291290 hasConcept C154945302 @default.
- W4313291290 hasConcept C185592680 @default.
- W4313291290 hasConcept C188027245 @default.
- W4313291290 hasConcept C2776401178 @default.
- W4313291290 hasConcept C31972630 @default.
- W4313291290 hasConcept C41008148 @default.
- W4313291290 hasConcept C41895202 @default.
- W4313291290 hasConcept C45347329 @default.
- W4313291290 hasConcept C50644808 @default.
- W4313291290 hasConcept C52102323 @default.
- W4313291290 hasConcept C52622490 @default.
- W4313291290 hasConcept C69744172 @default.
- W4313291290 hasConcept C71139939 @default.
- W4313291290 hasConceptScore W4313291290C115961682 @default.
- W4313291290 hasConceptScore W4313291290C138885662 @default.
- W4313291290 hasConceptScore W4313291290C153180895 @default.
- W4313291290 hasConceptScore W4313291290C154945302 @default.
- W4313291290 hasConceptScore W4313291290C185592680 @default.
- W4313291290 hasConceptScore W4313291290C188027245 @default.
- W4313291290 hasConceptScore W4313291290C2776401178 @default.
- W4313291290 hasConceptScore W4313291290C31972630 @default.
- W4313291290 hasConceptScore W4313291290C41008148 @default.
- W4313291290 hasConceptScore W4313291290C41895202 @default.
- W4313291290 hasConceptScore W4313291290C45347329 @default.
- W4313291290 hasConceptScore W4313291290C50644808 @default.
- W4313291290 hasConceptScore W4313291290C52102323 @default.
- W4313291290 hasConceptScore W4313291290C52622490 @default.
- W4313291290 hasConceptScore W4313291290C69744172 @default.
- W4313291290 hasConceptScore W4313291290C71139939 @default.
- W4313291290 hasFunder F4320321001 @default.
- W4313291290 hasIssue "7" @default.
- W4313291290 hasLocation W43132912901 @default.
- W4313291290 hasOpenAccess W4313291290 @default.
- W4313291290 hasPrimaryLocation W43132912901 @default.
- W4313291290 hasRelatedWork W1968716783 @default.