Matches in SemOpenAlex for { <https://semopenalex.org/work/W2957744218> ?p ?o ?g. }
- W2957744218 abstract "This paper proposes a method for head pose estimation from a single image. Previous methods often predict head poses through landmark or depth estimation and would require more computation than necessary. Our method is based on regression and feature aggregation. For having a compact model, we employ the soft stagewise regression scheme. Existing feature aggregation methods treat inputs as a bag of features and thus ignore their spatial relationship in a feature map. We propose to learn a fine-grained structure mapping for spatially grouping features before aggregation. The fine-grained structure provides part-based information and pooled values. By utilizing learnable and non-learnable importance over the spatial location, different model variants can be generated and form a complementary ensemble. Experiments show that our method outperforms the state-of-the-art methods including both the landmark-free ones and the ones based on landmark or depth estimation. With only a single RGB frame as input, our method even outperforms methods utilizing multi-modality information (RGB-D, RGB-Time) on estimating the yaw angle. Furthermore, the memory overhead of our model is 100 times smaller than those of previous methods." @default.
- W2957744218 created "2019-07-23" @default.
- W2957744218 creator A5002217153 @default.
- W2957744218 creator A5006990118 @default.
- W2957744218 creator A5019389546 @default.
- W2957744218 creator A5091722415 @default.
- W2957744218 date "2019-06-01" @default.
- W2957744218 modified "2023-10-12" @default.
- W2957744218 title "FSA-Net: Learning Fine-Grained Structure Aggregation for Head Pose Estimation From a Single Image" @default.
- W2957744218 cites W1573758649 @default.
- W2957744218 cites W1643185111 @default.
- W2957744218 cites W1855204404 @default.
- W2957744218 cites W1896788142 @default.
- W2957744218 cites W1925384340 @default.
- W2957744218 cites W1946919140 @default.
- W2957744218 cites W1976948919 @default.
- W2957744218 cites W1990937109 @default.
- W2957744218 cites W2012885984 @default.
- W2957744218 cites W2038952578 @default.
- W2957744218 cites W2047875689 @default.
- W2957744218 cites W2058961190 @default.
- W2957744218 cites W2082308025 @default.
- W2957744218 cites W2087681821 @default.
- W2957744218 cites W2088028039 @default.
- W2957744218 cites W2103924867 @default.
- W2957744218 cites W2117228865 @default.
- W2957744218 cites W2136000821 @default.
- W2957744218 cites W2149382413 @default.
- W2957744218 cites W2157285372 @default.
- W2957744218 cites W2215711223 @default.
- W2957744218 cites W2311778361 @default.
- W2957744218 cites W2510725918 @default.
- W2957744218 cites W2548780814 @default.
- W2957744218 cites W2589255576 @default.
- W2957744218 cites W2737047298 @default.
- W2957744218 cites W2737644856 @default.
- W2957744218 cites W2777921528 @default.
- W2957744218 cites W2798553619 @default.
- W2957744218 cites W2807744618 @default.
- W2957744218 cites W2891177538 @default.
- W2957744218 cites W2951019013 @default.
- W2957744218 cites W2954275231 @default.
- W2957744218 cites W2963176022 @default.
- W2957744218 cites W2963861381 @default.
- W2957744218 cites W2964014798 @default.
- W2957744218 cites W2964171387 @default.
- W2957744218 cites W3101998545 @default.
- W2957744218 cites W3104792420 @default.
- W2957744218 doi "https://doi.org/10.1109/cvpr.2019.00118" @default.
- W2957744218 hasPublicationYear "2019" @default.
- W2957744218 type Work @default.
- W2957744218 sameAs 2957744218 @default.
- W2957744218 citedByCount "176" @default.
- W2957744218 countsByYear W29577442182019 @default.
- W2957744218 countsByYear W29577442182020 @default.
- W2957744218 countsByYear W29577442182021 @default.
- W2957744218 countsByYear W29577442182022 @default.
- W2957744218 countsByYear W29577442182023 @default.
- W2957744218 crossrefType "proceedings-article" @default.
- W2957744218 hasAuthorship W2957744218A5002217153 @default.
- W2957744218 hasAuthorship W2957744218A5006990118 @default.
- W2957744218 hasAuthorship W2957744218A5019389546 @default.
- W2957744218 hasAuthorship W2957744218A5091722415 @default.
- W2957744218 hasConcept C111919701 @default.
- W2957744218 hasConcept C11413529 @default.
- W2957744218 hasConcept C138885662 @default.
- W2957744218 hasConcept C153180895 @default.
- W2957744218 hasConcept C154945302 @default.
- W2957744218 hasConcept C2776401178 @default.
- W2957744218 hasConcept C2779960059 @default.
- W2957744218 hasConcept C2780297707 @default.
- W2957744218 hasConcept C31972630 @default.
- W2957744218 hasConcept C41008148 @default.
- W2957744218 hasConcept C41895202 @default.
- W2957744218 hasConcept C45374587 @default.
- W2957744218 hasConcept C52102323 @default.
- W2957744218 hasConcept C52622490 @default.
- W2957744218 hasConcept C82990744 @default.
- W2957744218 hasConceptScore W2957744218C111919701 @default.
- W2957744218 hasConceptScore W2957744218C11413529 @default.
- W2957744218 hasConceptScore W2957744218C138885662 @default.
- W2957744218 hasConceptScore W2957744218C153180895 @default.
- W2957744218 hasConceptScore W2957744218C154945302 @default.
- W2957744218 hasConceptScore W2957744218C2776401178 @default.
- W2957744218 hasConceptScore W2957744218C2779960059 @default.
- W2957744218 hasConceptScore W2957744218C2780297707 @default.
- W2957744218 hasConceptScore W2957744218C31972630 @default.
- W2957744218 hasConceptScore W2957744218C41008148 @default.
- W2957744218 hasConceptScore W2957744218C41895202 @default.
- W2957744218 hasConceptScore W2957744218C45374587 @default.
- W2957744218 hasConceptScore W2957744218C52102323 @default.
- W2957744218 hasConceptScore W2957744218C52622490 @default.
- W2957744218 hasConceptScore W2957744218C82990744 @default.
- W2957744218 hasLocation W29577442181 @default.
- W2957744218 hasOpenAccess W2957744218 @default.
- W2957744218 hasPrimaryLocation W29577442181 @default.
- W2957744218 hasRelatedWork W1990932233 @default.
- W2957744218 hasRelatedWork W2004069545 @default.
- W2957744218 hasRelatedWork W2086478527 @default.
- W2957744218 hasRelatedWork W2154461499 @default.