Zobrazeno 1 - 10
of 14
pro vyhledávání: '"Pavel Tokmakov"'
Autor:
Boris Ivanovic, Kuan-Hui Lee, Pavel Tokmakov, Blake Wulfe, Rowan Mcllister, Adrien Gaidon, Marco Pavone
Publikováno v:
2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).
Reasoning about the future behavior of other agents is critical to safe robot navigation. The multiplicity of plausible futures is further amplified by the uncertainty inherent to agent state estimation from data, including positions, velocities, and
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::bccff7320fed0fa42896d0ab0e89db9c
https://doi.org/10.1109/iros47612.2022.9982283
https://doi.org/10.1109/iros47612.2022.9982283
This paper studies the problem of object discovery -- separating objects from the background without manual labels. Existing approaches utilize appearance cues, such as color, texture, and location, to group pixels into object-like regions. However,
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::069e1ad763db5405d5fe258724208723
Publikováno v:
ECCV Workshop-Visual Inductive Priors for Data-Efficient Deep Learning
ECCV Workshop-Visual Inductive Priors for Data-Efficient Deep Learning, Aug 2020, Edinburgh (online), United Kingdom
Computer Vision – ECCV 2020 Workshops ISBN: 9783030660956
ECCV Workshops (2)
ECCV Workshop-Visual Inductive Priors for Data-Efficient Deep Learning, Aug 2020, Edinburgh (online), United Kingdom
Computer Vision – ECCV 2020 Workshops ISBN: 9783030660956
ECCV Workshops (2)
International audience; This paper addresses the task of unsupervised learning of representations for action recognition in videos. Previous works proposed to utilize future prediction, or other domain-specific objectives to train a network, but achi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::68bd1779230eff2357611ec3a04b4423
https://inria.hal.science/hal-03990585/document
https://inria.hal.science/hal-03990585/document
Publikováno v:
Artificial Intelligence. 244:188-216
We propose relational linear programming, a simple framework for combining linear programs (LPs) and logic programs. A relational linear program (RLP) is a declarative LP template defining the objective and the constraints through the logical concept
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6c626a4ab33641bd9964f32eded86096
https://doi.org/10.1016/j.artint.2015.06.009
https://doi.org/10.1016/j.artint.2015.06.009
Publikováno v:
CVPR Workshops
Virtually all of deep learning literature relies on the assumption of large amounts of available training data. Indeed, even the majority of few-shot learning methods rely on a large set of "base classes" for pretraining. This assumption, however, do
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::faab3fa45125defc23dbb7f9d93dfb9d
http://arxiv.org/abs/1911.12911
http://arxiv.org/abs/1911.12911
Publikováno v:
ICCV
This paper addresses the task of learning latent attributes from triplet similarity comparisons. Consider, for instance, the three shoes in Fig. 1(a). They can be compared according to color, comfort, size, or shape resulting in different rankings. M
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::952c60b9600e59b9591640649d57ae25
https://doi.org/10.1109/iccv.2019.00049
https://doi.org/10.1109/iccv.2019.00049
Publikováno v:
ICCV
One of the key limitations of modern deep learning approaches lies in the amount of data required to train them. Humans, by contrast, can learn to recognize novel categories from just a few examples. Instrumental to this rapid learning ability is the
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7348a530f4870bfccc2a430d4c8319c8
https://doi.org/10.1109/iccv.2019.00647
https://doi.org/10.1109/iccv.2019.00647
Publikováno v:
International Journal of Computer Vision
International Journal of Computer Vision, Springer Verlag, 2019, 127 (3), pp.282-301. ⟨10.1007/s11263-018-1122-2⟩
International Journal of Computer Vision, 2019, 127 (3), pp.282-301. ⟨10.1007/s11263-018-1122-2⟩
International Journal of Computer Vision, Springer Verlag, 2019, 127 (3), pp.282-301. ⟨10.1007/s11263-018-1122-2⟩
International Journal of Computer Vision, 2019, 127 (3), pp.282-301. ⟨10.1007/s11263-018-1122-2⟩
We study the problem of segmenting moving objects in unconstrained videos. Given a video, the task is to segment all the objects that exhibit independent motion in at least one frame. We formulate this as a learning problem and design our framework w
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a4d00be30b96d46d47325cbdc4f8f7eb
https://hal.archives-ouvertes.fr/hal-01653720v2/document
https://hal.archives-ouvertes.fr/hal-01653720v2/document
Publikováno v:
ICCV Workshops
Detecting and segmenting individual objects, regardless of their category, is crucial for many applications such as action detection or robotic interaction. While this problem has been well-studied under the classic formulation of spatio-temporal gro
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ebeeffcd43acc152cfd99365d99b60fd
Publikováno v:
CVPR
A dominant paradigm for learning-based approaches in computer vision is training generic models, such as ResNet for image recognition, or I3D for video understanding, on large datasets and allowing them to discover the optimal representation for the
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b5e7bcce4d95ff754603e74e95067bdc