Zobrazeno 1 - 10
of 50
pro vyhledávání: '"Karteek Alahari"'
Publikováno v:
ICVGIP 2022-Indian Conference on Computer Vision, Graphics and Image Processing
ICVGIP 2022-Indian Conference on Computer Vision, Graphics and Image Processing, Dec 2022, Gandhinagar, India. pp.1-9
ICVGIP 2022-Indian Conference on Computer Vision, Graphics and Image Processing, Dec 2022, Gandhinagar, India. pp.1-9
International audience; Despite the progress seen in classification methods, current approaches for handling videos with distribution shifts in source and target domains remain source-dependent as they require access to the source data during the ada
Autor:
Lina Mezghani, Sainbayar Sukhbaatar, Thibaut Lavril, Oleksandr Maksymets, Dhruv Batra, Piotr Bojanowski, Karteek Alahari
Publikováno v:
IROS-IEEE/RSJ International Conference on Intelligent Robots and Systems
IROS-IEEE/RSJ International Conference on Intelligent Robots and Systems, Oct 2022, Kyoto, Japan
HAL
IROS-IEEE/RSJ International Conference on Intelligent Robots and Systems, Oct 2022, Kyoto, Japan
HAL
In this work, we address the problem of image-goal navigation in the context of visually-realistic 3D environments. This task involves navigating to a location indicated by a target image in a previously unseen environment. Earlier attempts, includin
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::addb3e98f000da27f8491a2fb9633b2e
https://inria.hal.science/hal-03110875
https://inria.hal.science/hal-03110875
Autor:
Enrico Fini, Victor G. Turrisi Da Costa, Xavier Alameda-Pineda, Elisa Ricci, Karteek Alahari, Julien Mairal
Publikováno v:
CVPR 2022-IEEE/CVF Conference on Computer Vision and Pattern Recognition
CVPR 2022-IEEE/CVF Conference on Computer Vision and Pattern Recognition, Jun 2022, New Orleans, United States. pp.9611-9620, ⟨10.1109/CVPR52688.2022.00940⟩
CVPR 2022-IEEE/CVF Conference on Computer Vision and Pattern Recognition, Jun 2022, New Orleans, United States. pp.9611-9620, ⟨10.1109/CVPR52688.2022.00940⟩
International audience; Self-supervised models have been shown to produce comparable or better visual representations than their supervised counterparts when trained offline on unlabeled data at scale. However, their efficacy is catastrophically redu
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d8262add4fab99b997aace86b7c0252f
http://arxiv.org/abs/2112.04215
http://arxiv.org/abs/2112.04215
Publikováno v:
Computer Vision and Image Understanding
Computer Vision and Image Understanding, 2023, 227, pp.103601. ⟨10.1016/j.cviu.2022.103601⟩
Computer Vision and Image Understanding, 2023, 227, pp.103601. ⟨10.1016/j.cviu.2022.103601⟩
Preprint. Under review; Vision-based depth estimation is a key feature in autonomous systems, which often relies on a single camera or several independent ones. In such a monocular setup, dense depth is obtained with either additional input from one
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1cd9088cb2a5e91be3cef49b605e5fd7
http://arxiv.org/abs/2109.03569
http://arxiv.org/abs/2109.03569
Publikováno v:
ICPR 2020-International Conference on Pattern Recognition
ICPR 2020-International Conference on Pattern Recognition, Jan 2021, Milan (Virtual), Italy. pp.10098-10105, ⟨10.1109/ICPR48806.2021.9412306⟩
ICPR
ICPR 2020-International Conference on Pattern Recognition, Jan 2021, Milan (Virtual), Italy. pp.10098-10105, ⟨10.1109/ICPR48806.2021.9412306⟩
ICPR
International audience; This paper addresses the task of group activity recognition in multi-person videos. Existing approaches decompose this task into feature learning and relational reasoning. Despite showing progress, these methods only rely on a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::db4449e3d1ad517224aee8f89da94f5b
https://hal.archives-ouvertes.fr/hal-02987414/document
https://hal.archives-ouvertes.fr/hal-02987414/document
Publikováno v:
ECCV 2020-European Conference on Computer Vision
ECCV 2020-European Conference on Computer Vision, Aug 2020, Glasgow, United Kingdom. pp.214-229, ⟨10.1007/978-3-030-58548-8_13⟩
Computer Vision – ECCV 2020 ISBN: 9783030585471
ECCV (4)
ECCV 2020-European Conference on Computer Vision, Aug 2020, Glasgow, United Kingdom. pp.214-229, ⟨10.1007/978-3-030-58548-8_13⟩
Computer Vision – ECCV 2020 ISBN: 9783030585471
ECCV (4)
The task of retrieving video content relevant to natural language queries plays a critical role in effectively handling internet-scale datasets. Most of the existing methods for this caption-to-video retrieval problem do not fully exploit cross-modal
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::513489b2ae2fd21294409c05b0b5b5c8
https://hal.inria.fr/hal-02903209
https://hal.inria.fr/hal-02903209
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
Autor:
Karteek Alahari
Publikováno v:
CoVieW@MM
Several theories in cognitive neuroscience suggest that when people interact with the world, or simulate interactions, they do so from a first-person egocentric perspective, and seamlessly transfer knowledge between third-person (observer) and first-
Publikováno v:
IEEE Transactions on Circuits and Systems for Video Technology
IEEE Transactions on Circuits and Systems for Video Technology, Institute of Electrical and Electronics Engineers, 2018, 28 (10), pp.3019-3029. ⟨10.1109/TCSVT.2017.2764624⟩
IEEE Transactions on Circuits and Systems for Video Technology, 2018, 28 (10), pp.3019-3029. ⟨10.1109/TCSVT.2017.2764624⟩
IEEE Transactions on Circuits and Systems for Video Technology, Institute of Electrical and Electronics Engineers, 2018, 28 (10), pp.3019-3029. ⟨10.1109/TCSVT.2017.2764624⟩
IEEE Transactions on Circuits and Systems for Video Technology, 2018, 28 (10), pp.3019-3029. ⟨10.1109/TCSVT.2017.2764624⟩
International audience; Traditional approaches for classifying event videos rely on a manually curated training dataset. While this paradigm has achieved excellent results on benchmarks such as TrecVid multimedia event detection (MED) challenge datas
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::105b0a270d33bc05431ba521eca5b092
https://hal.inria.fr/hal-01618400/document
https://hal.inria.fr/hal-01618400/document
Publikováno v:
Computer Vision and Image Understanding
Computer Vision and Image Understanding, 2016, 145, pp.30-42. ⟨10.1016/j.cviu.2016.01.002⟩
Computer Vision and Image Understanding, Elsevier, 2016, 145, pp.30-42. ⟨10.1016/j.cviu.2016.01.002⟩
Computer Vision and Image Understanding, 2016, 145, pp.30-42. ⟨10.1016/j.cviu.2016.01.002⟩
Computer Vision and Image Understanding, Elsevier, 2016, 145, pp.30-42. ⟨10.1016/j.cviu.2016.01.002⟩
An energy minimization based approach for scene text recognition with seamless integration of multiple cues.Applied also to the challenging open vocabulary setting, where a word-specific lexicon is unavailable.Comprehensive experimental evaluation on