Matches in SemOpenAlex for { <https://semopenalex.org/work/W2962823193> ?p ?o ?g. }
- W2962823193 abstract "Recent adversarial learning research has achieved very impressive progress for modelling cross-domain data shifts in appearance space but its counterpart in modelling cross-domain shifts in geometry space lags far behind. This paper presents an innovative Geometry-Aware Domain Adaptation Network (GA-DAN) that is capable of modelling cross-domain shifts concurrently in both geometry space and appearance space and realistically converting images across domains with very different characteristics. In the proposed GA-DAN, a novel multi-modal spatial learning technique is designed which converts a source-domain image into multiple images of different spatial views as in the target domain. A new disentangled cycle-consistency loss is introduced which balances the cycle consistency in appearance and geometry spaces and improves the learning of the whole network greatly. The proposed GA-DAN has been evaluated for the classic scene text detection and recognition tasks, and experiments show that the domain-adapted images achieve superior scene text detection and recognition performance while applied to network training." @default.
- W2962823193 created "2019-07-30" @default.
- W2962823193 creator A5023507910 @default.
- W2962823193 creator A5064046791 @default.
- W2962823193 creator A5068548252 @default.
- W2962823193 date "2019-07-22" @default.
- W2962823193 modified "2023-10-16" @default.
- W2962823193 title "GA-DAN: Geometry-Aware Domain Adaptation Network for Scene Text Detection and Recognition" @default.
- W2962823193 cites W117491841 @default.
- W2962823193 cites W1491389626 @default.
- W2962823193 cites W1710476689 @default.
- W2962823193 cites W1722318740 @default.
- W2962823193 cites W1895191496 @default.
- W2962823193 cites W1922126009 @default.
- W2962823193 cites W1935817682 @default.
- W2962823193 cites W1967140047 @default.
- W2962823193 cites W1971822075 @default.
- W2962823193 cites W1972065312 @default.
- W2962823193 cites W1978729128 @default.
- W2962823193 cites W1981283549 @default.
- W2962823193 cites W1990550880 @default.
- W2962823193 cites W1998042868 @default.
- W2962823193 cites W2019478948 @default.
- W2962823193 cites W2031342017 @default.
- W2962823193 cites W2053317383 @default.
- W2962823193 cites W2061802763 @default.
- W2962823193 cites W2128409098 @default.
- W2962823193 cites W2144554289 @default.
- W2962823193 cites W2146835493 @default.
- W2962823193 cites W2153182373 @default.
- W2962823193 cites W2194187530 @default.
- W2962823193 cites W2217433794 @default.
- W2962823193 cites W2239285313 @default.
- W2962823193 cites W2294053032 @default.
- W2962823193 cites W2339589954 @default.
- W2962823193 cites W2343052201 @default.
- W2962823193 cites W2411541852 @default.
- W2962823193 cites W2467286621 @default.
- W2962823193 cites W2511131004 @default.
- W2962823193 cites W2519818067 @default.
- W2962823193 cites W2532759528 @default.
- W2962823193 cites W2564591810 @default.
- W2962823193 cites W2584009249 @default.
- W2962823193 cites W2593768305 @default.
- W2962823193 cites W2598581049 @default.
- W2962823193 cites W2604243686 @default.
- W2962823193 cites W2605982830 @default.
- W2962823193 cites W2614453579 @default.
- W2962823193 cites W2750933790 @default.
- W2962823193 cites W2810028092 @default.
- W2962823193 cites W2831607544 @default.
- W2962823193 cites W2873558679 @default.
- W2962823193 cites W2875814315 @default.
- W2962823193 cites W2904785373 @default.
- W2962823193 cites W2911919580 @default.
- W2962823193 cites W2944310056 @default.
- W2962823193 cites W2962773189 @default.
- W2962823193 cites W2962793481 @default.
- W2962823193 cites W2962804639 @default.
- W2962823193 cites W2962808524 @default.
- W2962823193 cites W2962810613 @default.
- W2962823193 cites W2963073614 @default.
- W2962823193 cites W2963275094 @default.
- W2962823193 cites W2963299604 @default.
- W2962823193 cites W2963444790 @default.
- W2962823193 cites W2963517393 @default.
- W2962823193 cites W2963526661 @default.
- W2962823193 cites W2963684088 @default.
- W2962823193 cites W2963709863 @default.
- W2962823193 cites W2963712589 @default.
- W2962823193 cites W2963784072 @default.
- W2962823193 cites W2963826681 @default.
- W2962823193 cites W2963840241 @default.
- W2962823193 cites W2964018263 @default.
- W2962823193 cites W2964024144 @default.
- W2962823193 cites W2964065044 @default.
- W2962823193 cites W2964082390 @default.
- W2962823193 cites W2964278684 @default.
- W2962823193 cites W2964300754 @default.
- W2962823193 cites W648143168 @default.
- W2962823193 cites W70975097 @default.
- W2962823193 doi "https://doi.org/10.48550/arxiv.1907.09653" @default.
- W2962823193 hasPublicationYear "2019" @default.
- W2962823193 type Work @default.
- W2962823193 sameAs 2962823193 @default.
- W2962823193 citedByCount "0" @default.
- W2962823193 crossrefType "posted-content" @default.
- W2962823193 hasAuthorship W2962823193A5023507910 @default.
- W2962823193 hasAuthorship W2962823193A5064046791 @default.
- W2962823193 hasAuthorship W2962823193A5068548252 @default.
- W2962823193 hasBestOaLocation W29628231931 @default.
- W2962823193 hasConcept C111919701 @default.
- W2962823193 hasConcept C11413529 @default.
- W2962823193 hasConcept C115961682 @default.
- W2962823193 hasConcept C120665830 @default.
- W2962823193 hasConcept C121332964 @default.
- W2962823193 hasConcept C134306372 @default.
- W2962823193 hasConcept C139807058 @default.
- W2962823193 hasConcept C153180895 @default.
- W2962823193 hasConcept C154945302 @default.