Zobrazeno 1 - 10
of 28
pro vyhledávání: '"Viktor Seib"'
Autor:
Viktor Seib, Dietrich Paulus
Publikováno v:
2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8d1a3b391279ae6c5af97ada2bcc5885
https://doi.org/10.1109/iccvw54120.2021.00282
https://doi.org/10.1109/iccvw54120.2021.00282
Publikováno v:
ICARSC
Training a neural network typically requires large amounts of data. Yet, gathering such amounts of data may pose a problem. This can be addressed by augmenting a data set, i. e., by adding artificial data to the original data set. One method of augme
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a184fcb54a1d6cdff146354681917981
https://doi.org/10.1109/icarsc52212.2021.9429808
https://doi.org/10.1109/icarsc52212.2021.9429808
Autor:
Viktor Seib, Dietrich Paulus
Publikováno v:
ICARSC
Deep learning techniques have become the standard approach for computer vision tasks. However, traditional methods are still advantageous in application domains with limited computing or battery power such as mobile robots. In this work, we address t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::866b77e83f3852e1e11b05d70abd3218
https://doi.org/10.1109/icarsc52212.2021.9429775
https://doi.org/10.1109/icarsc52212.2021.9429775
Publikováno v:
ICARSC
In this paper we present an approach for learning to imitate human behavior on a semantic level by markerless visual observation. We analyze a set of spatial constraints on human pose data extracted using convolutional pose machines and object inform
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3f6d2848f13d5439a34359c33a63fb43
https://doi.org/10.1109/icarsc49921.2020.9096123
https://doi.org/10.1109/icarsc49921.2020.9096123
Publikováno v:
IROS
We present Simitate --- a hybrid benchmarking suite targeting the evaluation of approaches for imitation learning. A dataset containing 1938 sequences where humans perform daily activities in a realistic environment is presented. The dataset is stron
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c590a1bdede99ac77789f7c663e39fbb
http://arxiv.org/abs/1905.06002
http://arxiv.org/abs/1905.06002
Publikováno v:
RoboCup 2018: Robot World Cup XXII ISBN: 9783030275433
RoboCup
RoboCup
We won this year’s RoboCup@Home track in the Open Platform League in Montreal (Canada). The approaches as used for the competition are briefly described in this paper. The robotic hardware of our custom built robot Lisa and the PAL Robotics TIAGo,
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e80d2678772c46b34562640a3e1972ee
https://doi.org/10.1007/978-3-030-27544-0_42
https://doi.org/10.1007/978-3-030-27544-0_42
Publikováno v:
VISIGRAPP (5: VISAPP)
We present a competitive approach for 3D data classification that is related to Implicit Shape Models and Naive-Bayes Nearest Neighbor algorithms. Based on this approach we investigate methods to reduce the amount of data stored in the extracted code
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::74ad637ae8f44c7bab4dd8a69672463b
https://doi.org/10.5220/0007312400002108
https://doi.org/10.5220/0007312400002108
Publikováno v:
RoboCup 2019: Robot World Cup XXIII ISBN: 9783030356989
RoboCup
RoboCup
Team homer@UniKoblenz has become an integral part of the RoboCup@Home community. As such we would like to share our experience gained during the competitions with new teams. In this paper we describe our approaches with a special focus on our demonst
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ba3f2014fcf5fc01f673c13bb2aa3469
https://doi.org/10.1007/978-3-030-35699-6_46
https://doi.org/10.1007/978-3-030-35699-6_46
Publikováno v:
ICARSC
Scientific competitions are crucial in the field of service robotics. They foster knowledge exchange and allow teams to test their research in unstandardized scenarios and compare result. Such is the case of RoboCup@Home. However, keeping track of al
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::108867473561b61620fd50bbe875ecc9
Autor:
Viktor Seib, Dietrich Paulus
Publikováno v:
ICIP
Most feature descriptors need point normal information to be computed prior to computing the descriptor itself. We present a descriptor transform and apply it to the SHOT descriptor that allows to entirely omit the computation of normals. Further, ou
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::64c44537448ee3b7bc8b7511616deb53
https://doi.org/10.1109/icip.2018.8451849
https://doi.org/10.1109/icip.2018.8451849