Matches in SemOpenAlex for { <https://semopenalex.org/work/W3093565423> ?p ?o ?g. }
- W3093565423 endingPage "133" @default.
- W3093565423 startingPage "121" @default.
- W3093565423 abstract "Heatmap regression (HR) has become one of the mainstream approaches for face alignment and has obtained promising results under constrained environments. However, when a face image suffers from large pose variations, heavy occlusions and complicated illuminations, the performances of HR methods degrade greatly due to the low resolutions of the generated landmark heatmaps and the exclusion of important high-order information that can be used to learn more discriminative features. To address the alignment problem for faces with extremely large poses and heavy occlusions, this paper proposes a heatmap subpixel regression (HSR) method and a multi-order cross geometry-aware (MCG) model, which are seamlessly integrated into a novel multi-order high-precision hourglass network (MHHN). The HSR method is proposed to achieve high-precision landmark detection by a well-designed subpixel detection loss (SDL) and subpixel detection technology (SDT). At the same time, the MCG model is able to use the proposed multi-order cross information to learn more discriminative representations for enhancing facial geometric constraints and context information. To the best of our knowledge, this is the first study to explore heatmap subpixel regression for robust and high-precision face alignment. The experimental results from challenging benchmark datasets demonstrate that our approach outperforms state-of-the-art methods in the literature." @default.
- W3093565423 created "2020-10-29" @default.
- W3093565423 creator A5007226593 @default.
- W3093565423 creator A5008355957 @default.
- W3093565423 creator A5043352718 @default.
- W3093565423 creator A5049079081 @default.
- W3093565423 creator A5068442919 @default.
- W3093565423 date "2021-01-01" @default.
- W3093565423 modified "2023-10-14" @default.
- W3093565423 title "Robust Face Alignment by Multi-Order High-Precision Hourglass Network" @default.
- W3093565423 cites W1536775035 @default.
- W3093565423 cites W1796263212 @default.
- W3093565423 cites W1832881114 @default.
- W3093565423 cites W1896424170 @default.
- W3093565423 cites W1903029394 @default.
- W3093565423 cites W1977821862 @default.
- W3093565423 cites W1990937109 @default.
- W3093565423 cites W1998294030 @default.
- W3093565423 cites W2005264304 @default.
- W3093565423 cites W2032558548 @default.
- W3093565423 cites W2038952578 @default.
- W3093565423 cites W2087681821 @default.
- W3093565423 cites W2111372597 @default.
- W3093565423 cites W2130563197 @default.
- W3093565423 cites W2152826865 @default.
- W3093565423 cites W2157285372 @default.
- W3093565423 cites W2284800790 @default.
- W3093565423 cites W2437557374 @default.
- W3093565423 cites W2462523589 @default.
- W3093565423 cites W2518965973 @default.
- W3093565423 cites W2519753233 @default.
- W3093565423 cites W2554268477 @default.
- W3093565423 cites W2565639579 @default.
- W3093565423 cites W2731821979 @default.
- W3093565423 cites W2736671157 @default.
- W3093565423 cites W2736728583 @default.
- W3093565423 cites W2770121394 @default.
- W3093565423 cites W2776305063 @default.
- W3093565423 cites W2798730128 @default.
- W3093565423 cites W2798814244 @default.
- W3093565423 cites W2897558462 @default.
- W3093565423 cites W2900195156 @default.
- W3093565423 cites W2944892540 @default.
- W3093565423 cites W2954930822 @default.
- W3093565423 cites W2962708168 @default.
- W3093565423 cites W2962714886 @default.
- W3093565423 cites W2962925415 @default.
- W3093565423 cites W2962992847 @default.
- W3093565423 cites W2963519453 @default.
- W3093565423 cites W2963789946 @default.
- W3093565423 cites W2964014798 @default.
- W3093565423 cites W2964231884 @default.
- W3093565423 cites W2979854415 @default.
- W3093565423 cites W2986821660 @default.
- W3093565423 cites W2996037860 @default.
- W3093565423 doi "https://doi.org/10.1109/tip.2020.3032029" @default.
- W3093565423 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/33095713" @default.
- W3093565423 hasPublicationYear "2021" @default.
- W3093565423 type Work @default.
- W3093565423 sameAs 3093565423 @default.
- W3093565423 citedByCount "27" @default.
- W3093565423 countsByYear W30935654232020 @default.
- W3093565423 countsByYear W30935654232021 @default.
- W3093565423 countsByYear W30935654232022 @default.
- W3093565423 countsByYear W30935654232023 @default.
- W3093565423 crossrefType "journal-article" @default.
- W3093565423 hasAuthorship W3093565423A5007226593 @default.
- W3093565423 hasAuthorship W3093565423A5008355957 @default.
- W3093565423 hasAuthorship W3093565423A5043352718 @default.
- W3093565423 hasAuthorship W3093565423A5049079081 @default.
- W3093565423 hasAuthorship W3093565423A5068442919 @default.
- W3093565423 hasBestOaLocation W30935654232 @default.
- W3093565423 hasConcept C104317684 @default.
- W3093565423 hasConcept C105795698 @default.
- W3093565423 hasConcept C11413529 @default.
- W3093565423 hasConcept C127532173 @default.
- W3093565423 hasConcept C13280743 @default.
- W3093565423 hasConcept C144024400 @default.
- W3093565423 hasConcept C151730666 @default.
- W3093565423 hasConcept C153180895 @default.
- W3093565423 hasConcept C154945302 @default.
- W3093565423 hasConcept C155512373 @default.
- W3093565423 hasConcept C160633673 @default.
- W3093565423 hasConcept C166957645 @default.
- W3093565423 hasConcept C185592680 @default.
- W3093565423 hasConcept C185798385 @default.
- W3093565423 hasConcept C205649164 @default.
- W3093565423 hasConcept C2779304628 @default.
- W3093565423 hasConcept C2779343474 @default.
- W3093565423 hasConcept C2780297707 @default.
- W3093565423 hasConcept C31972630 @default.
- W3093565423 hasConcept C33923547 @default.
- W3093565423 hasConcept C36289849 @default.
- W3093565423 hasConcept C41008148 @default.
- W3093565423 hasConcept C55493867 @default.
- W3093565423 hasConcept C63479239 @default.
- W3093565423 hasConcept C68516990 @default.
- W3093565423 hasConcept C83546350 @default.