Matches in SemOpenAlex for { <https://semopenalex.org/work/W2977822667> ?p ?o ?g. }
- W2977822667 abstract "We present an adversarial deep domain adaptation (ADA) approach for training deep neural networks that estimate 3D pose and shape of a human from a single image. Existing datasets of in-the-wild images of humans have limited availability of 3D ground truth. We propose a novel deep architecture for 3D pose estimation and leverage the variations in pose, body shape and background in the synthetic datasets to train our network. Using ADA we adapt our network to real human images by designing a pipeline for joint 3D pose and shape estimation. Thus, we propose an ADA-based single-shot, straightforward, (no reprojection, no iterative refinement), end-to-end training approach via joint optimization on real and synthetic images. Through joint training on real and synthetic data, our network extracts features that are robust to domain shift. These features are then used to estimate the 3D mesh parameters in a single shot with no supervision on real samples. We compute the regression loss on synthetic samples with ground-truth mesh parameters. Knowledge is transferred from synthetic to real data through ADA without direct key point-based supervision." @default.
- W2977822667 created "2019-10-10" @default.
- W2977822667 creator A5009101133 @default.
- W2977822667 creator A5023595255 @default.
- W2977822667 date "2019-10-03" @default.
- W2977822667 modified "2023-10-04" @default.
- W2977822667 title "Single-Shot 3D Mesh Estimation via Adversarial Domain Adaptation" @default.
- W2977822667 cites W1677182931 @default.
- W2977822667 cites W1861492603 @default.
- W2977822667 cites W1943191679 @default.
- W2977822667 cites W1967554269 @default.
- W2977822667 cites W2080873731 @default.
- W2977822667 cites W2101032778 @default.
- W2977822667 cites W2122633688 @default.
- W2977822667 cites W2175012183 @default.
- W2977822667 cites W2194775991 @default.
- W2977822667 cites W2214409633 @default.
- W2977822667 cites W2312004824 @default.
- W2977822667 cites W2404595106 @default.
- W2977822667 cites W2554247908 @default.
- W2977822667 cites W2557698284 @default.
- W2977822667 cites W2559085405 @default.
- W2977822667 cites W2573098616 @default.
- W2977822667 cites W2576289912 @default.
- W2977822667 cites W2578797046 @default.
- W2977822667 cites W2583372902 @default.
- W2977822667 cites W2583585015 @default.
- W2977822667 cites W2584009249 @default.
- W2977822667 cites W2593768305 @default.
- W2977822667 cites W2604375920 @default.
- W2977822667 cites W2605947573 @default.
- W2977822667 cites W2611932403 @default.
- W2977822667 cites W2612706635 @default.
- W2977822667 cites W2742737904 @default.
- W2977822667 cites W2756050327 @default.
- W2977822667 cites W2758778552 @default.
- W2977822667 cites W2768591600 @default.
- W2977822667 cites W2777262900 @default.
- W2977822667 cites W2779380177 @default.
- W2977822667 cites W2788865504 @default.
- W2977822667 cites W2795889831 @default.
- W2977822667 cites W2797184202 @default.
- W2977822667 cites W2797515701 @default.
- W2977822667 cites W2798291180 @default.
- W2977822667 cites W2798414551 @default.
- W2977822667 cites W2798453135 @default.
- W2977822667 cites W2798593490 @default.
- W2977822667 cites W2798637590 @default.
- W2977822667 cites W2798646183 @default.
- W2977822667 cites W2798658180 @default.
- W2977822667 cites W2798714868 @default.
- W2977822667 cites W2798964604 @default.
- W2977822667 cites W2799107345 @default.
- W2977822667 cites W2806998878 @default.
- W2977822667 cites W2807725536 @default.
- W2977822667 cites W2810981979 @default.
- W2977822667 cites W2885722640 @default.
- W2977822667 cites W2895168809 @default.
- W2977822667 cites W2962754033 @default.
- W2977822667 cites W2962778061 @default.
- W2977822667 cites W2962823940 @default.
- W2977822667 cites W2962945654 @default.
- W2977822667 cites W2962976523 @default.
- W2977822667 cites W2963187488 @default.
- W2977822667 cites W2963314137 @default.
- W2977822667 cites W2963383668 @default.
- W2977822667 cites W2963403405 @default.
- W2977822667 cites W2963468256 @default.
- W2977822667 cites W2963475767 @default.
- W2977822667 cites W2963481481 @default.
- W2977822667 cites W2963506806 @default.
- W2977822667 cites W2963688992 @default.
- W2977822667 cites W2963791050 @default.
- W2977822667 cites W2963865469 @default.
- W2977822667 cites W2963876278 @default.
- W2977822667 cites W2963995996 @default.
- W2977822667 cites W2964055354 @default.
- W2977822667 cites W2964057616 @default.
- W2977822667 cites W2964070329 @default.
- W2977822667 cites W2964105113 @default.
- W2977822667 cites W2964221239 @default.
- W2977822667 cites W2964297864 @default.
- W2977822667 doi "https://doi.org/10.1007/s42979-019-0025-9" @default.
- W2977822667 hasPublicationYear "2019" @default.
- W2977822667 type Work @default.
- W2977822667 sameAs 2977822667 @default.
- W2977822667 citedByCount "1" @default.
- W2977822667 countsByYear W29778226672023 @default.
- W2977822667 crossrefType "journal-article" @default.
- W2977822667 hasAuthorship W2977822667A5009101133 @default.
- W2977822667 hasAuthorship W2977822667A5023595255 @default.
- W2977822667 hasBestOaLocation W29778226671 @default.
- W2977822667 hasConcept C108583219 @default.
- W2977822667 hasConcept C127413603 @default.
- W2977822667 hasConcept C131979681 @default.
- W2977822667 hasConcept C146849305 @default.
- W2977822667 hasConcept C153083717 @default.
- W2977822667 hasConcept C153180895 @default.
- W2977822667 hasConcept C154945302 @default.
- W2977822667 hasConcept C160920958 @default.