Matches in SemOpenAlex for { <https://semopenalex.org/work/W3132834324> ?p ?o ?g. }
- W3132834324 endingPage "280" @default.
- W3132834324 startingPage "266" @default.
- W3132834324 abstract "Thermal-to-visible face verification is a challenging problem due to the large domain discrepancy between the modalities. Existing approaches either attempt to synthesize visible faces from thermal faces or learn domain-invariant robust features from these modalities for cross-modal matching. In this paper, we use attributes extracted from visible images to synthesize attribute-preserved visible images from thermal imagery for cross-modal matching. A pre-trained attribute predictor network is used to extract the attributes from the visible image. Then, a novel multi-scale generator is proposed to synthesize the visible image from the thermal image guided by the extracted attributes. Finally, a pre-trained VGG-Face network is leveraged to extract features from the synthesized image and the input visible image for verification. Extensive experiments evaluated on three datasets (ARL Face Database, Visible and Thermal Paired Face Database, and Tufts Face Database) demonstrate that the proposed method achieves state-of-the-art performance. In particular, it achieves around 2.41%, 2.85% and 1.77% improvements in Equal Error Rate (EER) over the state-of-the-art methods on the ARL Face Database, Visible and Thermal Paired Face Database, and Tufts Face Database, respectively. An extended dataset (ARL Face Dataset volume III) consisting of polarimetric thermal faces of 121 subjects is also introduced in this paper. Furthermore, an ablation study is conducted to demonstrate the effectiveness of different modules in the proposed method." @default.
- W3132834324 created "2021-03-01" @default.
- W3132834324 creator A5002842383 @default.
- W3132834324 creator A5004716468 @default.
- W3132834324 creator A5013497247 @default.
- W3132834324 creator A5070603115 @default.
- W3132834324 creator A5075289214 @default.
- W3132834324 date "2021-04-01" @default.
- W3132834324 modified "2023-10-18" @default.
- W3132834324 title "Multi-Scale Thermal to Visible Face Verification via Attribute Guided Synthesis" @default.
- W3132834324 cites W1503965576 @default.
- W3132834324 cites W1895390915 @default.
- W3132834324 cites W1915485278 @default.
- W3132834324 cites W1971359334 @default.
- W3132834324 cites W1991410148 @default.
- W3132834324 cites W1998165562 @default.
- W3132834324 cites W2012648224 @default.
- W3132834324 cites W2021242760 @default.
- W3132834324 cites W2032213187 @default.
- W3132834324 cites W2043167551 @default.
- W3132834324 cites W2111233654 @default.
- W3132834324 cites W2117908922 @default.
- W3132834324 cites W2123052420 @default.
- W3132834324 cites W2146897752 @default.
- W3132834324 cites W2152788298 @default.
- W3132834324 cites W2204652942 @default.
- W3132834324 cites W2325939864 @default.
- W3132834324 cites W2331128040 @default.
- W3132834324 cites W2341788950 @default.
- W3132834324 cites W2485847574 @default.
- W3132834324 cites W2520774990 @default.
- W3132834324 cites W2551624499 @default.
- W3132834324 cites W2560023338 @default.
- W3132834324 cites W2566614872 @default.
- W3132834324 cites W2784025535 @default.
- W3132834324 cites W2895749211 @default.
- W3132834324 cites W2902038035 @default.
- W3132834324 cites W2902139631 @default.
- W3132834324 cites W2903798738 @default.
- W3132834324 cites W2904856314 @default.
- W3132834324 cites W2945521265 @default.
- W3132834324 cites W2963066927 @default.
- W3132834324 cites W2963073614 @default.
- W3132834324 cites W2963156682 @default.
- W3132834324 cites W2963163163 @default.
- W3132834324 cites W2963276927 @default.
- W3132834324 cites W2963294002 @default.
- W3132834324 cites W2963377935 @default.
- W3132834324 cites W2963383024 @default.
- W3132834324 cites W2963409068 @default.
- W3132834324 cites W2963413689 @default.
- W3132834324 cites W2963460857 @default.
- W3132834324 cites W2963639219 @default.
- W3132834324 cites W2963809521 @default.
- W3132834324 cites W2963968629 @default.
- W3132834324 cites W2964309429 @default.
- W3132834324 cites W2964323748 @default.
- W3132834324 cites W2969985801 @default.
- W3132834324 cites W2998039742 @default.
- W3132834324 cites W3006602891 @default.
- W3132834324 cites W3099206234 @default.
- W3132834324 cites W3101998545 @default.
- W3132834324 cites W3102910076 @default.
- W3132834324 cites W4255016102 @default.
- W3132834324 cites W4376848235 @default.
- W3132834324 cites W845365781 @default.
- W3132834324 doi "https://doi.org/10.1109/tbiom.2021.3060641" @default.
- W3132834324 hasPublicationYear "2021" @default.
- W3132834324 type Work @default.
- W3132834324 sameAs 3132834324 @default.
- W3132834324 citedByCount "16" @default.
- W3132834324 countsByYear W31328343242021 @default.
- W3132834324 countsByYear W31328343242022 @default.
- W3132834324 countsByYear W31328343242023 @default.
- W3132834324 crossrefType "journal-article" @default.
- W3132834324 hasAuthorship W3132834324A5002842383 @default.
- W3132834324 hasAuthorship W3132834324A5004716468 @default.
- W3132834324 hasAuthorship W3132834324A5013497247 @default.
- W3132834324 hasAuthorship W3132834324A5070603115 @default.
- W3132834324 hasAuthorship W3132834324A5075289214 @default.
- W3132834324 hasBestOaLocation W31328343242 @default.
- W3132834324 hasConcept C105795698 @default.
- W3132834324 hasConcept C115961682 @default.
- W3132834324 hasConcept C121332964 @default.
- W3132834324 hasConcept C144024400 @default.
- W3132834324 hasConcept C153180895 @default.
- W3132834324 hasConcept C154945302 @default.
- W3132834324 hasConcept C165064840 @default.
- W3132834324 hasConcept C185592680 @default.
- W3132834324 hasConcept C188027245 @default.
- W3132834324 hasConcept C2778755073 @default.
- W3132834324 hasConcept C2779304628 @default.
- W3132834324 hasConcept C31510193 @default.
- W3132834324 hasConcept C31972630 @default.
- W3132834324 hasConcept C33923547 @default.
- W3132834324 hasConcept C36289849 @default.
- W3132834324 hasConcept C41008148 @default.
- W3132834324 hasConcept C62520636 @default.