Zobrazeno 1 - 10
of 15
pro vyhledávání: '"Chris Bregler"'
Publikováno v:
CVPR
In this paper, we present a video-based learning framework for animating personalized 3D talking faces from audio. We introduce two training-time data normalizations that significantly improve data sample efficiency. First, we isolate and represent f
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c4f7cf32789a33e7275eebdb2ff345ad
https://doi.org/10.1109/cvpr46437.2021.00278
https://doi.org/10.1109/cvpr46437.2021.00278
Autor:
Arjun Gopalan, Qin Cao, Chris Bregler, Georg Fritz Osang, Vaiva Imbrasaite, Jannis Bulian, Ricardo Abasolo Marino, Gabriel Ilharco, Roma Patel, Lucas Smaira, Gabriel Fedrigo Barcik, Afsaneh Hajiamin Shirazi, Felipe Ferreira, Jared Frank, Arsha Nagrani, Cesar Ilharco, Blaz Bratanic, Thomas Leung, Christina Funk
Publikováno v:
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing: Tutorial Abstracts.
How information is created, shared and consumed has changed rapidly in recent decades, in part thanks to new social platforms and technologies on the web. With ever-larger amounts of unstructured and limited labels, organizing and reconciling informa
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a706b2140499a932a5858d105f1856f1
https://doi.org/10.18653/v1/2021.acl-tutorials.6
https://doi.org/10.18653/v1/2021.acl-tutorials.6
Autor:
Tyler Zhu, George Papandreou, Alexander Toshev, Chris Bregler, Kevin Murphy, Jonathan Tompson, Nori Kanazawa
Publikováno v:
CVPR
We propose a method for multi-person detection and 2-D pose estimation that achieves state-of-art results on the challenging COCO keypoints task. It is a simple, yet powerful, top-down approach consisting of two stages. In the first stage, we predict
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5a0444506ef68fce98e1ed2723f3be50
https://doi.org/10.1109/cvpr.2017.395
https://doi.org/10.1109/cvpr.2017.395
Publikováno v:
ACM Transactions on Graphics. 32:1-10
We introduce a real-time and calibration-free facial performance capture framework based on a sensor with video and depth input. In this framework, we develop an adaptive PCA model using shape correctives that adjust on-the-fly to the actor's express
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b11d31851aed6a4113c87f403a97dd05
https://doi.org/10.1145/2461912.2462019
https://doi.org/10.1145/2461912.2462019
Publikováno v:
ACM Multimedia
Dance is a dynamic art form that reflects a wide range of cultural diversity and individuality. With the advancement of motion-capture technology combined with crowd-sourcing and machine learning algorithms, we explore the complex relationship betwee
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::141ad856e025f6ec466e30d2f44304b8
https://doi.org/10.1145/2733373.2806220
https://doi.org/10.1145/2733373.2806220
Autor:
Arjun Jain, E. de Aguiar, Christian Theobalt, Ahmed Elhayek, Mykhaylo Andriluka, Bernt Schiele, Chris Bregler, Jonathan Tompson, Leonid Pishchulin
Publikováno v:
CVPR
We present a novel method for accurate marker-less capture of articulated skeleton motion of several subjects in general scenes, indoors and outdoors, even from input filmed with as few as two cameras. Our approach unites a discriminative image-based
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::2cbe5b38fba0f2a4b7c650e4dc906a27
https://doi.org/10.1109/cvpr.2015.7299005
https://doi.org/10.1109/cvpr.2015.7299005
Autor:
Doug DeCarlo, Chris Bregler, Alyssa Lees, Christian Rodriguez, Insuk Oh, Adrian Stere, Matthew Stone
Publikováno v:
ACM Transactions on Graphics. 23:506-513
We describe a method for using a database of recorded speech and captured motion to create an animated conversational character. People's utterances are composed of short, clearly-delimited phrases; in each phrase, gesture and speech go together mean
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4c189aded8f29844c68d405f1aa0fc0c
https://doi.org/10.1145/1015706.1015753
https://doi.org/10.1145/1015706.1015753
Publikováno v:
CVPR Workshops
In this study we present robust solution for estimating 3D pose and shape of human targets from multiple, synchronized video streams. The objective is to automatically estimate physical attributes of the targets that would allow us to analyze its beh
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c0769973ee5201c8bd8d0f748627dfd2
https://doi.org/10.1109/cvprw.2011.5981821
https://doi.org/10.1109/cvprw.2011.5981821
Publikováno v:
ICPR
This paper shows how “Body Motion Signature Analysis” – a new “soft-biometrics” technique – can be used for identity verification. It is able to extract motion features from the upper body of people and estimates so called “super-featur
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ddb1955ee43b465755f78af6fc743d9d
https://doi.org/10.1109/icpr.2010.538
https://doi.org/10.1109/icpr.2010.538