Zobrazeno 1 - 10
of 315
pro vyhledávání: '"Trevor Darrell"'
Autor:
Jinkyu Kim, Anna Rohrbach, Zeynep Akata, Suhong Moon, Teruhisa Misu, Yi‐Ting Chen, Trevor Darrell, John Canny
Publikováno v:
Applied AI Letters, Vol 2, Iss 4, Pp n/a-n/a (2021)
Abstract Humans learn to drive through both practice and theory, for example, by studying the rules, while most self‐driving systems are limited to the former. Being able to incorporate human knowledge of typical causal driving behavior should bene
Externí odkaz:
https://doaj.org/article/0b03332c2c2646a1a21cfb885107a291
Autor:
Olivia Watkins, Sandy Huang, Julius Frost, Kush Bhatia, Eric Weiner, Pieter Abbeel, Trevor Darrell, Bryan Plummer, Kate Saenko, Anca Dragan
Publikováno v:
Applied AI Letters, Vol 2, Iss 4, Pp n/a-n/a (2021)
Abstract In order to interact with a robot or make wise decisions about where and how to deploy it in the real world, humans need to have an accurate mental model of how the robot acts in different situations. We propose to improve users' mental mode
Externí odkaz:
https://doaj.org/article/4a45e57a3c934206a2404bdbc0f3f702
Publikováno v:
Applied AI Letters, Vol 2, Iss 4, Pp n/a-n/a (2021)
Abstract In complex inferential tasks like question answering, machine learning models must confront two challenges: the need to implement a compositional reasoning process, and, in many applications, the need for this reasoning process to be interpr
Externí odkaz:
https://doaj.org/article/70c88cb6375c4fac84d305ef5a8207ea
Publikováno v:
Applied AI Letters, Vol 2, Iss 4, Pp n/a-n/a (2021)
Abstract We generate natural language explanations for a fine‐grained visual recognition task. Our explanations fulfill two criteria. First, explanations are class discriminative, meaning they mention attributes in an image which are important to i
Externí odkaz:
https://doaj.org/article/69ed6439dccc42589defb07bc3c6e376
Autor:
Sayna Ebrahimi, Suzanne Petryk, Akash Gokul, William Gan, Joseph E. Gonzalez, Marcus Rohrbach, Trevor Darrell
Publikováno v:
Applied AI Letters, Vol 2, Iss 4, Pp n/a-n/a (2021)
Abstract The goal of continual learning (CL) is to learn a sequence of tasks without suffering from the phenomenon of catastrophic forgetting. Previous work has shown that leveraging memory in the form of a replay buffer can reduce performance degrad
Externí odkaz:
https://doaj.org/article/8711bb1171054479b9a053b73ba90b0e
Advances in computational geometry and machine learning that offer new methods for search, regression, and classification with large amounts of high-dimensional data. Regression and classification methods based on similarity of the input to stored ex
Publikováno v:
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).
Natural language applied to natural 2D images describes a fundamentally 3D world. We present the Voxel-informed Language Grounder (VLG), a language grounding model that leverages 3D geometric information in the form of voxel maps derived from the vis
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::46d08f5e982b4c550bb0516a12d7b220
http://arxiv.org/abs/2205.09710
http://arxiv.org/abs/2205.09710
We present a framework for modeling interactional communication in dyadic conversations: given multimodal inputs of a speaker, we autoregressively output multiple possibilities of corresponding listener motion. We combine the motion and speech audio
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::bdcadbd6efb5f3f36f790af2245023e1
http://arxiv.org/abs/2204.08451
http://arxiv.org/abs/2204.08451
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783031200526
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::adb37a7244dd85124f75169f401089a3
https://doi.org/10.1007/978-3-031-20053-3_16
https://doi.org/10.1007/978-3-031-20053-3_16