Matches in SemOpenAlex for { <https://semopenalex.org/work/W4328137122> ?p ?o ?g. }
Showing items 1 to 97 of
97
with 100 items per page.
- W4328137122 endingPage "119922" @default.
- W4328137122 startingPage "119922" @default.
- W4328137122 abstract "3D hand pose estimation methods have made significant progress recently. However, estimation accuracy is often far from sufficient for specific real-world applications, and thus there is significant room for improvement. This paper proposes TriHorn-Net, a novel model that uses specific innovations to improve hand pose estimation accuracy on depth images. The first innovation is decomposition of the 3D hand pose estimation into the estimation of 2D joint locations in the depth image space (UV), and the estimation of their corresponding depths aided by two complementary attention maps. This decomposition prevents depth estimation, which is a more difficult task, from interfering with the UV estimations at both the prediction and feature levels. The second innovation is PixDropout, which is, to the best of our knowledge, the first appearance-based data augmentation method for hand depth images. Experimental results demonstrate that the proposed model outperforms the state-of-the-art methods on three public benchmark datasets, achieving 5.73 mm, 7.13 mm, and 7.68 mm on the ICVL, MSRA, and NYU datasets, respectively. The proposed model achieves this performance with a relatively fast average inference speed of 9.25 ms per frame on an NVIDIA 1080Ti GPU, which, as discussed in the paper, places the proposed model among the fastest-performing 3D hand pose estimation models. Our implementation is available at https://github.com/mrezaei92/TriHorn-Net." @default.
- W4328137122 created "2023-03-22" @default.
- W4328137122 creator A5025213339 @default.
- W4328137122 creator A5026295038 @default.
- W4328137122 creator A5073490125 @default.
- W4328137122 date "2023-08-01" @default.
- W4328137122 modified "2023-09-25" @default.
- W4328137122 title "TriHorn-Net: A model for accurate depth-based 3D hand pose estimation" @default.
- W4328137122 cites W1928739709 @default.
- W4328137122 cites W1974700302 @default.
- W4328137122 cites W2075156252 @default.
- W4328137122 cites W2093414253 @default.
- W4328137122 cites W2100642335 @default.
- W4328137122 cites W2218414108 @default.
- W4328137122 cites W2469784314 @default.
- W4328137122 cites W2737305288 @default.
- W4328137122 cites W2750326862 @default.
- W4328137122 cites W2768683308 @default.
- W4328137122 cites W2796453247 @default.
- W4328137122 cites W2796717907 @default.
- W4328137122 cites W2798581336 @default.
- W4328137122 cites W2799191197 @default.
- W4328137122 cites W2889123596 @default.
- W4328137122 cites W2903283814 @default.
- W4328137122 cites W2951006673 @default.
- W4328137122 cites W2962067162 @default.
- W4328137122 cites W2962811204 @default.
- W4328137122 cites W2963119249 @default.
- W4328137122 cites W2963402313 @default.
- W4328137122 cites W2963508807 @default.
- W4328137122 cites W2963598138 @default.
- W4328137122 cites W2963950354 @default.
- W4328137122 cites W2981561950 @default.
- W4328137122 cites W2998508940 @default.
- W4328137122 cites W3014641072 @default.
- W4328137122 cites W4230133199 @default.
- W4328137122 doi "https://doi.org/10.1016/j.eswa.2023.119922" @default.
- W4328137122 hasPublicationYear "2023" @default.
- W4328137122 type Work @default.
- W4328137122 citedByCount "0" @default.
- W4328137122 crossrefType "journal-article" @default.
- W4328137122 hasAuthorship W4328137122A5025213339 @default.
- W4328137122 hasAuthorship W4328137122A5026295038 @default.
- W4328137122 hasAuthorship W4328137122A5073490125 @default.
- W4328137122 hasBestOaLocation W43281371222 @default.
- W4328137122 hasConcept C126042441 @default.
- W4328137122 hasConcept C13280743 @default.
- W4328137122 hasConcept C153180895 @default.
- W4328137122 hasConcept C154945302 @default.
- W4328137122 hasConcept C162324750 @default.
- W4328137122 hasConcept C185798385 @default.
- W4328137122 hasConcept C187736073 @default.
- W4328137122 hasConcept C205649164 @default.
- W4328137122 hasConcept C2776214188 @default.
- W4328137122 hasConcept C2780451532 @default.
- W4328137122 hasConcept C31972630 @default.
- W4328137122 hasConcept C36613465 @default.
- W4328137122 hasConcept C41008148 @default.
- W4328137122 hasConcept C52102323 @default.
- W4328137122 hasConcept C76155785 @default.
- W4328137122 hasConcept C96250715 @default.
- W4328137122 hasConceptScore W4328137122C126042441 @default.
- W4328137122 hasConceptScore W4328137122C13280743 @default.
- W4328137122 hasConceptScore W4328137122C153180895 @default.
- W4328137122 hasConceptScore W4328137122C154945302 @default.
- W4328137122 hasConceptScore W4328137122C162324750 @default.
- W4328137122 hasConceptScore W4328137122C185798385 @default.
- W4328137122 hasConceptScore W4328137122C187736073 @default.
- W4328137122 hasConceptScore W4328137122C205649164 @default.
- W4328137122 hasConceptScore W4328137122C2776214188 @default.
- W4328137122 hasConceptScore W4328137122C2780451532 @default.
- W4328137122 hasConceptScore W4328137122C31972630 @default.
- W4328137122 hasConceptScore W4328137122C36613465 @default.
- W4328137122 hasConceptScore W4328137122C41008148 @default.
- W4328137122 hasConceptScore W4328137122C52102323 @default.
- W4328137122 hasConceptScore W4328137122C76155785 @default.
- W4328137122 hasConceptScore W4328137122C96250715 @default.
- W4328137122 hasLocation W43281371221 @default.
- W4328137122 hasLocation W43281371222 @default.
- W4328137122 hasOpenAccess W4328137122 @default.
- W4328137122 hasPrimaryLocation W43281371221 @default.
- W4328137122 hasRelatedWork W1968716783 @default.
- W4328137122 hasRelatedWork W2004095265 @default.
- W4328137122 hasRelatedWork W2064877078 @default.
- W4328137122 hasRelatedWork W2076468506 @default.
- W4328137122 hasRelatedWork W2085100591 @default.
- W4328137122 hasRelatedWork W2128635338 @default.
- W4328137122 hasRelatedWork W2154613448 @default.
- W4328137122 hasRelatedWork W2286009621 @default.
- W4328137122 hasRelatedWork W2567319754 @default.
- W4328137122 hasRelatedWork W4306804934 @default.
- W4328137122 hasVolume "223" @default.
- W4328137122 isParatext "false" @default.
- W4328137122 isRetracted "false" @default.
- W4328137122 workType "article" @default.