Matches in SemOpenAlex for { <https://semopenalex.org/work/W2892019541> ?p ?o ?g. }
- W2892019541 endingPage "49575" @default.
- W2892019541 startingPage "49563" @default.
- W2892019541 abstract "Recent studies show that convolutional neural networks (CNNs) has made a series of breakthroughs in the two tasks of face detection and pose estimation, respectively. There are two CNN frameworks for solving these two integrated tasks simultaneously. One is to use face detection network to detect faces firstly, and then use pose estimation network to estimate each face’s pose; the other is to use region proposal algorithm to generate many candidate regions that may contain faces, and then use a single deep multi-task CNN to process these regions for simultaneous face detection and pose estimation. The former’s problem is pose estimation’s performance is affected by face detection network because two networks are separate. The latter generates lots of candidate regions, which will bring huge computation cost to CNN and can’t achieve real-time. To solve the above existing problems, we propose a multi-task CNN cascade framework that integrates these two tasks. We show that multi-task learning of face detection and head pose estimation helps to extract more representative features. We exploit CNN feature fusion strategy to further improve head pose estimation’s performance. We evaluate face detection on FDDB benchmark, and evaluate pose estimation on AFW benchmark. Our method achieves comparative result compared with state-of-the-art in these two tasks and can achieve real-time performance." @default.
- W2892019541 created "2018-09-27" @default.
- W2892019541 creator A5021196481 @default.
- W2892019541 creator A5027398178 @default.
- W2892019541 creator A5030064573 @default.
- W2892019541 date "2018-01-01" @default.
- W2892019541 modified "2023-10-18" @default.
- W2892019541 title "Simultaneous Face Detection and Pose Estimation Using Convolutional Neural Network Cascade" @default.
- W2892019541 cites W149902725 @default.
- W2892019541 cites W1849007038 @default.
- W2892019541 cites W1896424170 @default.
- W2892019541 cites W1905153633 @default.
- W2892019541 cites W1934410531 @default.
- W2892019541 cites W1948751323 @default.
- W2892019541 cites W1974744233 @default.
- W2892019541 cites W1998808035 @default.
- W2892019541 cites W2012885984 @default.
- W2892019541 cites W2018326367 @default.
- W2892019541 cites W2022508996 @default.
- W2892019541 cites W204612701 @default.
- W2892019541 cites W2047875689 @default.
- W2892019541 cites W2056025798 @default.
- W2892019541 cites W2056695679 @default.
- W2892019541 cites W2088049833 @default.
- W2892019541 cites W2121601095 @default.
- W2892019541 cites W2125653371 @default.
- W2892019541 cites W2144354855 @default.
- W2892019541 cites W2145287260 @default.
- W2892019541 cites W2149382413 @default.
- W2892019541 cites W2157176527 @default.
- W2892019541 cites W2160532515 @default.
- W2892019541 cites W2162741153 @default.
- W2892019541 cites W2164598857 @default.
- W2892019541 cites W2168356304 @default.
- W2892019541 cites W2169696215 @default.
- W2892019541 cites W2170110077 @default.
- W2892019541 cites W2194775991 @default.
- W2892019541 cites W2209882149 @default.
- W2892019541 cites W2217896605 @default.
- W2892019541 cites W2473640056 @default.
- W2892019541 cites W2547715144 @default.
- W2892019541 cites W2548780814 @default.
- W2892019541 cites W2579152745 @default.
- W2892019541 cites W2589255576 @default.
- W2892019541 cites W2963037989 @default.
- W2892019541 cites W2963377935 @default.
- W2892019541 cites W2963566548 @default.
- W2892019541 cites W2963770578 @default.
- W2892019541 cites W2964014798 @default.
- W2892019541 cites W2964095005 @default.
- W2892019541 cites W300523764 @default.
- W2892019541 cites W3099206234 @default.
- W2892019541 cites W3101998545 @default.
- W2892019541 cites W3104792420 @default.
- W2892019541 cites W7746136 @default.
- W2892019541 doi "https://doi.org/10.1109/access.2018.2869465" @default.
- W2892019541 hasPublicationYear "2018" @default.
- W2892019541 type Work @default.
- W2892019541 sameAs 2892019541 @default.
- W2892019541 citedByCount "28" @default.
- W2892019541 countsByYear W28920195412019 @default.
- W2892019541 countsByYear W28920195412020 @default.
- W2892019541 countsByYear W28920195412021 @default.
- W2892019541 countsByYear W28920195412022 @default.
- W2892019541 countsByYear W28920195412023 @default.
- W2892019541 crossrefType "journal-article" @default.
- W2892019541 hasAuthorship W2892019541A5021196481 @default.
- W2892019541 hasAuthorship W2892019541A5027398178 @default.
- W2892019541 hasAuthorship W2892019541A5030064573 @default.
- W2892019541 hasBestOaLocation W28920195411 @default.
- W2892019541 hasConcept C13280743 @default.
- W2892019541 hasConcept C138885662 @default.
- W2892019541 hasConcept C144024400 @default.
- W2892019541 hasConcept C153180895 @default.
- W2892019541 hasConcept C154945302 @default.
- W2892019541 hasConcept C162324750 @default.
- W2892019541 hasConcept C185592680 @default.
- W2892019541 hasConcept C185798385 @default.
- W2892019541 hasConcept C187736073 @default.
- W2892019541 hasConcept C205649164 @default.
- W2892019541 hasConcept C2776401178 @default.
- W2892019541 hasConcept C2779304628 @default.
- W2892019541 hasConcept C2780451532 @default.
- W2892019541 hasConcept C31510193 @default.
- W2892019541 hasConcept C31972630 @default.
- W2892019541 hasConcept C34146451 @default.
- W2892019541 hasConcept C36289849 @default.
- W2892019541 hasConcept C41008148 @default.
- W2892019541 hasConcept C41895202 @default.
- W2892019541 hasConcept C43617362 @default.
- W2892019541 hasConcept C4641261 @default.
- W2892019541 hasConcept C52102323 @default.
- W2892019541 hasConcept C52622490 @default.
- W2892019541 hasConcept C81363708 @default.
- W2892019541 hasConceptScore W2892019541C13280743 @default.
- W2892019541 hasConceptScore W2892019541C138885662 @default.
- W2892019541 hasConceptScore W2892019541C144024400 @default.
- W2892019541 hasConceptScore W2892019541C153180895 @default.