Matches in SemOpenAlex for { <https://semopenalex.org/work/W2971639707> ?p ?o ?g. }
- W2971639707 abstract "Establishing semantic correspondence is a core problem in computer vision and remains challenging due to large intra-class variations and lack of annotated data. In this paper, we aim to incorporate global semantic context in a flexible manner to overcome the limitations of prior work that relies on local semantic representations. To this end, we first propose a context-aware semantic representation that incorporates spatial layout for robust matching against local ambiguities. We then develop a novel dynamic fusion strategy based on attention mechanism to weave the advantages of both local and context features by integrating semantic cues from multiple scales. We instantiate our strategy by designing an end-to-end learnable deep network, named as Dynamic Context Correspondence Network (DCCNet). To train the network, we adopt a multi-auxiliary task loss to improve the efficiency of our weakly-supervised learning procedure. Our approach achieves superior or competitive performance over previous methods on several challenging datasets, including PF-Pascal, PF-Willow, and TSS, demonstrating its effectiveness and generality." @default.
- W2971639707 created "2019-09-12" @default.
- W2971639707 creator A5015970030 @default.
- W2971639707 creator A5038936840 @default.
- W2971639707 creator A5064995424 @default.
- W2971639707 creator A5072694881 @default.
- W2971639707 creator A5073702793 @default.
- W2971639707 date "2019-09-08" @default.
- W2971639707 modified "2023-10-16" @default.
- W2971639707 title "Dynamic Context Correspondence Network for Semantic Alignment" @default.
- W2971639707 cites W1522301498 @default.
- W2971639707 cites W2003511559 @default.
- W2971639707 cites W2013640163 @default.
- W2971639707 cites W2090518410 @default.
- W2971639707 cites W2104853049 @default.
- W2971639707 cites W2104974755 @default.
- W2971639707 cites W2116645175 @default.
- W2971639707 cites W2117248802 @default.
- W2971639707 cites W2144502914 @default.
- W2971639707 cites W2163446794 @default.
- W2971639707 cites W2194775991 @default.
- W2971639707 cites W2464606141 @default.
- W2971639707 cites W2518982800 @default.
- W2971639707 cites W2535410496 @default.
- W2971639707 cites W2556967412 @default.
- W2971639707 cites W2566812041 @default.
- W2971639707 cites W2593948489 @default.
- W2971639707 cites W2604233003 @default.
- W2971639707 cites W2604881841 @default.
- W2971639707 cites W2630837129 @default.
- W2971639707 cites W2736876108 @default.
- W2971639707 cites W2751023760 @default.
- W2971639707 cites W2885650013 @default.
- W2971639707 cites W2886782161 @default.
- W2971639707 cites W2899771611 @default.
- W2971639707 cites W2947841945 @default.
- W2971639707 cites W2958407526 @default.
- W2971639707 cites W2962891704 @default.
- W2971639707 cites W2963020784 @default.
- W2971639707 cites W2963091558 @default.
- W2971639707 cites W2963325280 @default.
- W2971639707 cites W2964073646 @default.
- W2971639707 cites W2964141676 @default.
- W2971639707 cites W2964188292 @default.
- W2971639707 cites W2435623039 @default.
- W2971639707 doi "https://doi.org/10.48550/arxiv.1909.03444" @default.
- W2971639707 hasPublicationYear "2019" @default.
- W2971639707 type Work @default.
- W2971639707 sameAs 2971639707 @default.
- W2971639707 citedByCount "0" @default.
- W2971639707 crossrefType "posted-content" @default.
- W2971639707 hasAuthorship W2971639707A5015970030 @default.
- W2971639707 hasAuthorship W2971639707A5038936840 @default.
- W2971639707 hasAuthorship W2971639707A5064995424 @default.
- W2971639707 hasAuthorship W2971639707A5072694881 @default.
- W2971639707 hasAuthorship W2971639707A5073702793 @default.
- W2971639707 hasBestOaLocation W29716397071 @default.
- W2971639707 hasConcept C105795698 @default.
- W2971639707 hasConcept C119857082 @default.
- W2971639707 hasConcept C151730666 @default.
- W2971639707 hasConcept C154945302 @default.
- W2971639707 hasConcept C15744967 @default.
- W2971639707 hasConcept C162324750 @default.
- W2971639707 hasConcept C165064840 @default.
- W2971639707 hasConcept C187736073 @default.
- W2971639707 hasConcept C199360897 @default.
- W2971639707 hasConcept C204321447 @default.
- W2971639707 hasConcept C2778493491 @default.
- W2971639707 hasConcept C2779343474 @default.
- W2971639707 hasConcept C2780451532 @default.
- W2971639707 hasConcept C2780767217 @default.
- W2971639707 hasConcept C33923547 @default.
- W2971639707 hasConcept C41008148 @default.
- W2971639707 hasConcept C542102704 @default.
- W2971639707 hasConcept C64754055 @default.
- W2971639707 hasConcept C75608658 @default.
- W2971639707 hasConcept C86803240 @default.
- W2971639707 hasConceptScore W2971639707C105795698 @default.
- W2971639707 hasConceptScore W2971639707C119857082 @default.
- W2971639707 hasConceptScore W2971639707C151730666 @default.
- W2971639707 hasConceptScore W2971639707C154945302 @default.
- W2971639707 hasConceptScore W2971639707C15744967 @default.
- W2971639707 hasConceptScore W2971639707C162324750 @default.
- W2971639707 hasConceptScore W2971639707C165064840 @default.
- W2971639707 hasConceptScore W2971639707C187736073 @default.
- W2971639707 hasConceptScore W2971639707C199360897 @default.
- W2971639707 hasConceptScore W2971639707C204321447 @default.
- W2971639707 hasConceptScore W2971639707C2778493491 @default.
- W2971639707 hasConceptScore W2971639707C2779343474 @default.
- W2971639707 hasConceptScore W2971639707C2780451532 @default.
- W2971639707 hasConceptScore W2971639707C2780767217 @default.
- W2971639707 hasConceptScore W2971639707C33923547 @default.
- W2971639707 hasConceptScore W2971639707C41008148 @default.
- W2971639707 hasConceptScore W2971639707C542102704 @default.
- W2971639707 hasConceptScore W2971639707C64754055 @default.
- W2971639707 hasConceptScore W2971639707C75608658 @default.
- W2971639707 hasConceptScore W2971639707C86803240 @default.
- W2971639707 hasLocation W29716397071 @default.
- W2971639707 hasOpenAccess W2971639707 @default.
- W2971639707 hasPrimaryLocation W29716397071 @default.