Matches in SemOpenAlex for { <https://semopenalex.org/work/W2959103553> ?p ?o ?g. }
- W2959103553 abstract "We present a deep learning-based multitask framework for joint 3D human pose estimation and action recognition from RGB video sequences. Our approach proceeds along two stages. In the first, we run a real-time 2D pose detector to determine the precise pixel location of important keypoints of the body. A two-stream neural network is then designed and trained to map detected 2D keypoints into 3D poses. In the second, we deploy the Efficient Neural Architecture Search (ENAS) algorithm to find an optimal network architecture that is used for modeling the spatio-temporal evolution of the estimated 3D poses via an image-based intermediate representation and performing action recognition. Experiments on Human3.6M, MSR Action3D and SBU Kinect Interaction datasets verify the effectiveness of the proposed method on the targeted tasks. Moreover, we show that our method requires a low computational budget for training and inference." @default.
- W2959103553 created "2019-07-23" @default.
- W2959103553 creator A5000226831 @default.
- W2959103553 creator A5024327401 @default.
- W2959103553 creator A5026219433 @default.
- W2959103553 creator A5065112274 @default.
- W2959103553 creator A5080971261 @default.
- W2959103553 creator A5090437430 @default.
- W2959103553 date "2019-07-16" @default.
- W2959103553 modified "2023-09-27" @default.
- W2959103553 title "A Unified Deep Framework for Joint 3D Pose Estimation and Action Recognition from a Single RGB Camera." @default.
- W2959103553 cites W1522301498 @default.
- W2959103553 cites W1600744878 @default.
- W2959103553 cites W1677182931 @default.
- W2959103553 cites W1744759976 @default.
- W2959103553 cites W1836465849 @default.
- W2959103553 cites W1904365287 @default.
- W2959103553 cites W1912967058 @default.
- W2959103553 cites W1950788856 @default.
- W2959103553 cites W1977039804 @default.
- W2959103553 cites W2030061193 @default.
- W2959103553 cites W2046033161 @default.
- W2959103553 cites W2046589395 @default.
- W2959103553 cites W2048821851 @default.
- W2959103553 cites W2056898157 @default.
- W2959103553 cites W2058256495 @default.
- W2959103553 cites W2068915126 @default.
- W2959103553 cites W2079447555 @default.
- W2959103553 cites W2098339052 @default.
- W2959103553 cites W2101032778 @default.
- W2959103553 cites W2111727626 @default.
- W2959103553 cites W2142194269 @default.
- W2959103553 cites W2143267104 @default.
- W2959103553 cites W2144380653 @default.
- W2959103553 cites W2145546283 @default.
- W2959103553 cites W2151103935 @default.
- W2959103553 cites W2155196764 @default.
- W2959103553 cites W2161866293 @default.
- W2959103553 cites W2181300449 @default.
- W2959103553 cites W2184544926 @default.
- W2959103553 cites W2194775991 @default.
- W2959103553 cites W2271991549 @default.
- W2959103553 cites W2274287116 @default.
- W2959103553 cites W2293220651 @default.
- W2959103553 cites W2307770531 @default.
- W2959103553 cites W2502928967 @default.
- W2959103553 cites W2510185399 @default.
- W2959103553 cites W2515603221 @default.
- W2959103553 cites W2518108298 @default.
- W2959103553 cites W2519758495 @default.
- W2959103553 cites W2522527348 @default.
- W2959103553 cites W2533739470 @default.
- W2959103553 cites W2553303224 @default.
- W2959103553 cites W2554247908 @default.
- W2959103553 cites W2556782416 @default.
- W2959103553 cites W2559085405 @default.
- W2959103553 cites W2604375920 @default.
- W2959103553 cites W2606294640 @default.
- W2959103553 cites W2611932403 @default.
- W2959103553 cites W2612706635 @default.
- W2959103553 cites W2736995747 @default.
- W2959103553 cites W2778523960 @default.
- W2959103553 cites W2785641712 @default.
- W2959103553 cites W2788865504 @default.
- W2959103553 cites W2789500342 @default.
- W2959103553 cites W2791303549 @default.
- W2959103553 cites W2797184202 @default.
- W2959103553 cites W2887446291 @default.
- W2959103553 cites W2903549000 @default.
- W2959103553 cites W2928146714 @default.
- W2959103553 cites W2947169932 @default.
- W2959103553 cites W2962746461 @default.
- W2959103553 cites W2963282966 @default.
- W2959103553 cites W2963446712 @default.
- W2959103553 cites W2963454111 @default.
- W2959103553 cites W2963592930 @default.
- W2959103553 cites W2963688992 @default.
- W2959103553 cites W2963840672 @default.
- W2959103553 cites W2964134613 @default.
- W2959103553 cites W2964135318 @default.
- W2959103553 cites W3123784868 @default.
- W2959103553 hasPublicationYear "2019" @default.
- W2959103553 type Work @default.
- W2959103553 sameAs 2959103553 @default.
- W2959103553 citedByCount "2" @default.
- W2959103553 countsByYear W29591035532020 @default.
- W2959103553 crossrefType "posted-content" @default.
- W2959103553 hasAuthorship W2959103553A5000226831 @default.
- W2959103553 hasAuthorship W2959103553A5024327401 @default.
- W2959103553 hasAuthorship W2959103553A5026219433 @default.
- W2959103553 hasAuthorship W2959103553A5065112274 @default.
- W2959103553 hasAuthorship W2959103553A5080971261 @default.
- W2959103553 hasAuthorship W2959103553A5090437430 @default.
- W2959103553 hasConcept C108583219 @default.
- W2959103553 hasConcept C121332964 @default.
- W2959103553 hasConcept C126042441 @default.
- W2959103553 hasConcept C127413603 @default.
- W2959103553 hasConcept C153180895 @default.
- W2959103553 hasConcept C154945302 @default.
- W2959103553 hasConcept C160633673 @default.