Matches in SemOpenAlex for { <https://semopenalex.org/work/W2247274765> ?p ?o ?g. }
- W2247274765 endingPage "223" @default.
- W2247274765 startingPage "211" @default.
- W2247274765 abstract "We propose a method to address challenges in unconstrained face detection, such as arbitrary pose variations and occlusions. First, a new image feature called Normalized Pixel Difference (NPD) is proposed. NPD feature is computed as the difference to sum ratio between two pixel values, inspired by the Weber Fraction in experimental psychology. The new feature is scale invariant, bounded, and is able to reconstruct the original image. Second, we propose a deep quadratic tree to learn the optimal subset of NPD features and their combinations, so that complex face manifolds can be partitioned by the learned rules. This way, only a single soft-cascade classifier is needed to handle unconstrained face detection. Furthermore, we show that the NPD features can be efficiently obtained from a look up table, and the detection template can be easily scaled, making the proposed face detector very fast. Experimental results on three public face datasets (FDDB, GENKI, and CMU-MIT) show that the proposed method achieves state-of-the-art performance in detecting unconstrained faces with arbitrary pose variations and occlusions in cluttered scenes." @default.
- W2247274765 created "2016-06-24" @default.
- W2247274765 creator A5007029060 @default.
- W2247274765 creator A5019092879 @default.
- W2247274765 creator A5082786719 @default.
- W2247274765 date "2016-02-01" @default.
- W2247274765 modified "2023-10-14" @default.
- W2247274765 title "A Fast and Accurate Unconstrained Face Detector" @default.
- W2247274765 cites W1480320979 @default.
- W2247274765 cites W1532425025 @default.
- W2247274765 cites W1966822758 @default.
- W2247274765 cites W1970563743 @default.
- W2247274765 cites W1992047056 @default.
- W2247274765 cites W2012885984 @default.
- W2247274765 cites W2015268479 @default.
- W2247274765 cites W2022154621 @default.
- W2247274765 cites W2024046085 @default.
- W2247274765 cites W2056025798 @default.
- W2247274765 cites W2097458023 @default.
- W2247274765 cites W2100588357 @default.
- W2247274765 cites W2100807570 @default.
- W2247274765 cites W2107634464 @default.
- W2247274765 cites W2111617188 @default.
- W2247274765 cites W2115812588 @default.
- W2247274765 cites W2119605622 @default.
- W2247274765 cites W2121601095 @default.
- W2247274765 cites W2130258210 @default.
- W2247274765 cites W2140274257 @default.
- W2247274765 cites W2141129816 @default.
- W2247274765 cites W2151129315 @default.
- W2247274765 cites W2153281406 @default.
- W2247274765 cites W2161877343 @default.
- W2247274765 cites W2163352848 @default.
- W2247274765 cites W2164598857 @default.
- W2247274765 cites W2169066052 @default.
- W2247274765 cites W2169696215 @default.
- W2247274765 cites W2170110077 @default.
- W2247274765 doi "https://doi.org/10.1109/tpami.2015.2448075" @default.
- W2247274765 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/26761729" @default.
- W2247274765 hasPublicationYear "2016" @default.
- W2247274765 type Work @default.
- W2247274765 sameAs 2247274765 @default.
- W2247274765 citedByCount "231" @default.
- W2247274765 countsByYear W22472747652015 @default.
- W2247274765 countsByYear W22472747652016 @default.
- W2247274765 countsByYear W22472747652017 @default.
- W2247274765 countsByYear W22472747652018 @default.
- W2247274765 countsByYear W22472747652019 @default.
- W2247274765 countsByYear W22472747652020 @default.
- W2247274765 countsByYear W22472747652021 @default.
- W2247274765 countsByYear W22472747652022 @default.
- W2247274765 countsByYear W22472747652023 @default.
- W2247274765 crossrefType "journal-article" @default.
- W2247274765 hasAuthorship W2247274765A5007029060 @default.
- W2247274765 hasAuthorship W2247274765A5019092879 @default.
- W2247274765 hasAuthorship W2247274765A5082786719 @default.
- W2247274765 hasBestOaLocation W22472747652 @default.
- W2247274765 hasConcept C129844170 @default.
- W2247274765 hasConcept C134306372 @default.
- W2247274765 hasConcept C138885662 @default.
- W2247274765 hasConcept C144024400 @default.
- W2247274765 hasConcept C153180895 @default.
- W2247274765 hasConcept C154945302 @default.
- W2247274765 hasConcept C160633673 @default.
- W2247274765 hasConcept C185592680 @default.
- W2247274765 hasConcept C190470478 @default.
- W2247274765 hasConcept C2524010 @default.
- W2247274765 hasConcept C2776401178 @default.
- W2247274765 hasConcept C2779304628 @default.
- W2247274765 hasConcept C31510193 @default.
- W2247274765 hasConcept C31972630 @default.
- W2247274765 hasConcept C33923547 @default.
- W2247274765 hasConcept C34146451 @default.
- W2247274765 hasConcept C34388435 @default.
- W2247274765 hasConcept C36289849 @default.
- W2247274765 hasConcept C37914503 @default.
- W2247274765 hasConcept C41008148 @default.
- W2247274765 hasConcept C41895202 @default.
- W2247274765 hasConcept C43617362 @default.
- W2247274765 hasConcept C4641261 @default.
- W2247274765 hasConcept C52622490 @default.
- W2247274765 hasConcept C76155785 @default.
- W2247274765 hasConcept C94915269 @default.
- W2247274765 hasConcept C95623464 @default.
- W2247274765 hasConceptScore W2247274765C129844170 @default.
- W2247274765 hasConceptScore W2247274765C134306372 @default.
- W2247274765 hasConceptScore W2247274765C138885662 @default.
- W2247274765 hasConceptScore W2247274765C144024400 @default.
- W2247274765 hasConceptScore W2247274765C153180895 @default.
- W2247274765 hasConceptScore W2247274765C154945302 @default.
- W2247274765 hasConceptScore W2247274765C160633673 @default.
- W2247274765 hasConceptScore W2247274765C185592680 @default.
- W2247274765 hasConceptScore W2247274765C190470478 @default.
- W2247274765 hasConceptScore W2247274765C2524010 @default.
- W2247274765 hasConceptScore W2247274765C2776401178 @default.
- W2247274765 hasConceptScore W2247274765C2779304628 @default.
- W2247274765 hasConceptScore W2247274765C31510193 @default.
- W2247274765 hasConceptScore W2247274765C31972630 @default.