Zobrazeno 1 - 10
of 33
pro vyhledávání: '"Moin Nabi"'
Autor:
Guanglei Yang, Enrico Fini, Dan Xu, Paolo Rota, Mingli Ding, Moin Nabi, Xavier Alameda-Pineda, Elisa Ricci
Publikováno v:
IEEE Transactions on Pattern Analysis and Machine Intelligence
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022, pp.1-14. ⟨10.1109/TPAMI.2022.3163806⟩
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022, pp.1-14. ⟨10.1109/TPAMI.2022.3163806⟩
A fundamental and challenging problem in deep learning is catastrophic forgetting, i.e. the tendency of neural networks to fail to preserve the knowledge acquired from old tasks when learning new tasks. This problem has been widely investigated in th
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6f92f0c45bc886a88a83e45ba4e50f85
https://inria.hal.science/hal-03908664
https://inria.hal.science/hal-03908664
Autor:
Tassilo Klein, Moin Nabi
Publikováno v:
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers).
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783030781903
IPMI
IPMI
Self-supervised learning approaches leverage unlabeled samples to acquire generic knowledge about different concepts, hence allowing for annotation-efficient downstream task learning. In this paper, we propose a novel self-supervised method that leve
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4689d379358a910aa55b447bc44fb025
https://doi.org/10.1007/978-3-030-78191-0_51
https://doi.org/10.1007/978-3-030-78191-0_51
Publikováno v:
European Conference on Computer Vision
European Conference on Computer Vision, Aug 2020, edinburgh, United Kingdom
Computer Vision – ECCV 2020 ISBN: 9783030586034
ECCV (28)
European Conference on Computer Vision, Aug 2020, edinburgh, United Kingdom
Computer Vision – ECCV 2020 ISBN: 9783030586034
ECCV (28)
Continual Learning (CL) aims to develop agents emulating the human ability to sequentially learn new tasks while being able to retain knowledge obtained from past experiences. In this paper, we introduce the novel problem of Memory-Constrained Online
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f010fde3f88fe5f8c08f20d36c707ca6
https://hal.telecom-paris.fr/hal-02941923
https://hal.telecom-paris.fr/hal-02941923
Autor:
Mahdyar Ravanbakhsh, Vadim Tschernezki, Felix Last, Tassilo Klein, Kayhan Batmanghelich, Volker Tresp, Moin Nabi
Publikováno v:
ICASSP
Proc IEEE Int Conf Acoust Speech Signal Process
Proc IEEE Int Conf Acoust Speech Signal Process
Image segmentation is a ubiquitous step in almost any medical image study. Deep learning-based approaches achieve state-of-the-art in the majority of image segmentation benchmarks. However, end-to-end training of such models requires sufficient annot
Publikováno v:
WACV
Although providing exceptional results for many computer vision tasks, state-of-the-art deep learning algorithms catastrophically struggle in low data scenarios. However, if data in additional modalities exist (e.g. text) this can compensate for the
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c3f018b008e63b6269c05c822c0b1173
Publikováno v:
International Journal of Machine Learning and Cybernetics. 9:1999-2010
In this paper, two novel descriptors are introduced to detect and localize abnormal behaviors in crowded scenes. The first proposed descriptor is based on the orientation and magnitude of short trajectories extracted by tracking interest points in sp
Autor:
Daniel Dorda, Moin Nabi
Publikováno v:
ICCV Workshops
This work analyses the sources of complexity in scene graph proposal problems, and develops a mathematical framework for efficiently designing synthetic relationship models. An entropy based metric is proposed for measuring the ambiguity of relationa
Publikováno v:
ICCV Workshops
One-shot learning is a challenging discipline of machine learning since it gnaws at the concept of learning from large amounts of data. This is akin to making machine learning algorithms generalize from a few examples, much like how humans learn. We
Publikováno v:
ICASSP
High performance of deep learning models typically comes at cost of considerable model size and computation time. These factors limit applicability for deployment on memory and battery constrained devices such as mobile phones or embedded systems. In