Zobrazeno 1 - 10
of 11
pro vyhledávání: '"Mihai Zanfir"'
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783031200434
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::50fdc4c4f2d6601207fb572f97a778ee
https://doi.org/10.1007/978-3-031-20044-1_41
https://doi.org/10.1007/978-3-031-20044-1_41
Publikováno v:
CVPR
I went to the gym today, but how well did I do? And where should I improve? Ah, my back hurts slightly... User engagement can be sustained and injuries avoided by being able to reconstruct 3d human pose and motion, relate it to good training practice
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4508bb9770393f4084ce498519a5d030
https://doi.org/10.1109/cvpr46437.2021.00979
https://doi.org/10.1109/cvpr46437.2021.00979
Autor:
Mihai Zanfir, Andrei Zanfir, Eduard Gabriel Bazavan, William T. Freeman, Rahul Sukthankar, Cristian Sminchisescu
We present THUNDR, a transformer-based deep neural network methodology to reconstruct the 3d pose and shape of people, given monocular RGB images. Key to our methodology is an intermediate 3d marker representation, where we aim to combine the predict
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3bd88a8c4f1a19fd704c93eaa5ecd2eb
Autor:
Mihai Zanfir, Cristian Sminchisescu, Rahul Sukthankar, Andrei Zanfir, Eduard Gabriel Bazavan, William T. Freeman
Publikováno v:
CVPR
We present deep neural network methodology to reconstruct the 3d pose and shape of people, given an input RGB image. We rely on a recently introduced, expressivefull body statistical 3d human model, GHUM, trained end-to-end, and learn to reconstruct
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9cb8784b9007e13783089730972271db
http://arxiv.org/abs/2008.06910
http://arxiv.org/abs/2008.06910
Autor:
Alin-Ionut Popa, Mihai Fieraru, Mihai Zanfir, Cristian Sminchisescu, Elisabeta Oneata, Vlad Olaru
Publikováno v:
CVPR
Understanding 3d human interactions is fundamental for fine grained scene analysis and behavioural modeling. However, most of the existing models focus on analyzing a single person in isolation, and those who process several people focus largely on r
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4dda7784eda65325770f748a26d36313
https://doi.org/10.1109/cvpr42600.2020.00724
https://doi.org/10.1109/cvpr42600.2020.00724
Publikováno v:
AAAI
Generating good quality and geometrically plausible synthetic images of humans with the ability to control appearance, pose and shape parameters, has become increasingly important for a variety of tasks ranging from photo editing, fashion virtual try
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3d9541cb093f423f1538f5b4bb823a36
Publikováno v:
2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
CVPR
CVPR
We introduce new, fine-grained action and emotion recognition tasks defined on non-staged videos, recorded during robot-assisted therapy sessions of children with autism. The tasks present several challenges: a large dataset with long videos, a large
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d09c3d101db7e032649a7e90dc004baa
Publikováno v:
2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
CVPR
CVPR
We propose a deep multitask architecture for \emph{fully automatic 2d and 3d human sensing} (DMHS), including \emph{recognition and reconstruction}, in \emph{monocular images}. The system computes the figure-ground segmentation, semantically identifi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::23301cd0134c993fd66649c69ed8180f
Publikováno v:
Computer Vision – ACCV 2016 ISBN: 9783319541891
ACCV (4)
ACCV (4)
Automatic video captioning is challenging due to the complex interactions in dynamic real scenes. A comprehensive system would ultimately localize and track the objects, actions and interactions present in a video and generate a description that reli
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::78dcdaaa3a32a3a3d3e71102a8040229
https://doi.org/10.1007/978-3-319-54190-7_7
https://doi.org/10.1007/978-3-319-54190-7_7
Publikováno v:
ICCV
Human action recognition under low observational latency is receiving a growing interest in computer vision due to rapidly developing technologies in human-robot interaction, computer gaming and surveillance. In this paper we propose a fast, simple,
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::2922b2241fb2a256094fc75be74a017e
https://doi.org/10.1109/iccv.2013.342
https://doi.org/10.1109/iccv.2013.342