Zobrazeno 1 - 10
of 18
pro vyhledávání: '"Luca Weihs"'
Publikováno v:
Communications of the ACM. 64:78-84
A large-scale, up-to-date analysis of Computer Science literature (11.8M papers through 2019) reveals that, if trends from the last 50 years continue, parity between the number of male and female authors will not be reached in this century. In contra
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5941f4c1917794c1236112e34ff87915
https://doi.org/10.1145/3430803
https://doi.org/10.1145/3430803
Contrastive language image pretraining (CLIP) encoders have been shown to be beneficial for a range of visual tasks from classification and detection to captioning and image manipulation. We investigate the effectiveness of CLIP visual backbones for
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f5ee298045c692b63b6da2e1ef616e84
http://arxiv.org/abs/2111.09888
http://arxiv.org/abs/2111.09888
Publikováno v:
CVPR
We have observed significant progress in visual navigation for embodied agents. A common assumption in studying visual navigation is that the environments are static; this is a limiting assumption. Intelligent navigation may involve interacting with
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e1ba492fd72d2472eef430bb19ac23bd
http://arxiv.org/abs/2104.14040
http://arxiv.org/abs/2104.14040
Publikováno v:
CVPR
There has been a significant recent progress in the field of Embodied AI with researchers developing models and algorithms enabling embodied agents to navigate and interact within completely unseen environments. In this paper, we propose a new datase
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::511ed732fba1f80ba224acec4e2af284
http://arxiv.org/abs/2103.16544
http://arxiv.org/abs/2103.16544
Deep reinforcement learning has shown promising results on an abundance of robotic tasks in simulation, including visual navigation and manipulation. Prior work generally aims to build embodied agents that solve their assigned tasks as quickly as pos
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d9286a4695a78ce71f04c0b3162dc4df
Autor:
Aniruddha Kembhavi, Alvaro Herrasti, Roozbeh Mottaghi, Kiana Ehsani, Eric Kolve, Winson Han, Eli VanderBilt, Luca Weihs
Publikováno v:
CVPR
The domain of Embodied AI has recently witnessed substantial progress, particularly in navigating agents within their environments. These early successes have laid the building blocks for the community to tackle tasks that require agents to actively
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c19091fd85e6e57695868bf6dd892198
Publikováno v:
Bernoulli 26, no. 4 (2020), 2503-2540
Directed graphical models specify noisy functional relationships among a collection of random variables. In the Gaussian case, each such model corresponds to a semi-algebraic set of positive definite covariance matrices. The set is given via a parame
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7ead8a46d979bf554dac9d816af992c0
https://doi.org/10.3150/19-bej1179
https://doi.org/10.3150/19-bej1179
Publikováno v:
CVPR
In this paper we address the problem of visual reaction: the task of interacting with dynamic environments where the changes in the environment are not necessarily caused by the agent itself. Visual reaction entails predicting the future changes in a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8144be20eeb764b201a8d43c975b352b
https://doi.org/10.1109/cvpr42600.2020.01159
https://doi.org/10.1109/cvpr42600.2020.01159
Publikováno v:
Biometrika. 105:547-562
SummaryThe need to test whether two random vectors are independent has spawned many competing measures of dependence. We focus on nonparametric measures that are invariant under strictly increasing transformations, such as Kendall’s tau, Hoeffding
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::111b1d1dabcb8e7c03c1d542579d6e8d
https://doi.org/10.1093/biomet/asy021
https://doi.org/10.1093/biomet/asy021
Autor:
Unnat Jain, Ali Farhadi, Alexander G. Schwing, Svetlana Lazebnik, Aniruddha Kembhavi, Eric Kolve, Luca Weihs
Publikováno v:
Computer Vision – ECCV 2020 ISBN: 9783030585570
ECCV (5)
ECCV (5)
Autonomous agents must learn to collaborate. It is not scalable to develop a new centralized agent every time a task’s difficulty outpaces a single agent’s abilities. While multi-agent collaboration research has flourished in gridworld-like envir
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::38dce8c2f1e3050ca1122d69de7ff8de
https://doi.org/10.1007/978-3-030-58558-7_28
https://doi.org/10.1007/978-3-030-58558-7_28