Zobrazeno 1 - 10
of 25
pro vyhledávání: '"Pham, Nam Trung"'
Autor:
Binici, Kuluhan, Aggarwal, Shivam, Acar, Cihan, Pham, Nam Trung, Leman, Karianto, Lee, Gim Hee, Mitra, Tulika
Knowledge distillation (KD) is a key element in neural network compression that allows knowledge transfer from a pre-trained teacher model to a more compact student model. KD relies on access to the training dataset, which may not always be fully ava
Externí odkaz:
http://arxiv.org/abs/2408.13850
Data-Free Knowledge Distillation (KD) allows knowledge transfer from a trained neural network (teacher) to a more compact one (student) in the absence of original training data. Existing works use a validation set to monitor the accuracy of the stude
Externí odkaz:
http://arxiv.org/abs/2201.03019
Publikováno v:
Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2022, pp. 663-671
With the increasing popularity of deep learning on edge devices, compressing large neural networks to meet the hardware requirements of resource-constrained devices became a significant research direction. Numerous compression methodologies are curre
Externí odkaz:
http://arxiv.org/abs/2108.05698
Autor:
Pham, Nam Trung, Le Cadre, Jean-Pierre
Publikováno v:
In IFAC Proceedings Volumes 2009 42(10):1387-1392
Autor:
Vu, Hai Quan, Pham, Nam Trung, Nguyen, Duc Hoang Ha, Huynh, Bao Toan, Le, Hoai Bac, Hoang, Kiem
Publikováno v:
Language, Information and Computation : Proceedings of the 17th Pacific Asia Conference, 1-3 October, 2003, Sentosa, Singapore. :416-422
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=jairo_______::549b7df0082990fab4fb1d3c2b761d0b
http://hdl.handle.net/2065/12298
http://hdl.handle.net/2065/12298
Publikováno v:
RIVF
This paper introduces a general traffic tracking system which has the ability to detect and track objects moving in the street automatically. By combining the idea of Particle Filter and background subtraction, we propose ODAPF - Object Detection Aid
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::562f34c3419966eb73b92d17f51b137f
https://doi.org/10.1109/rivf.2006.1696446
https://doi.org/10.1109/rivf.2006.1696446
Publikováno v:
ICPR (3)
In this paper, we propose an approach based on hidden Markov model (HMM) and linguistics for the Vietnamese recognition problem, including handwritten word and speech recognition. The main contribution is that our method can be used to model all Viet
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::219e78896282a5a14f702c8cbae2cbe1
https://doi.org/10.1109/icpr.2002.1048080
https://doi.org/10.1109/icpr.2002.1048080
Publikováno v:
ICDAR
The authors present a system for recognizing Vietnamese document images and propose a method to increase the accuracy for this system. Based on features of the Vietnamese language, we can minimize the number of characters and integrate spell-checking
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a71ce69e849dacf6c1e35bfa4e089c8a
https://doi.org/10.1109/icdar.2001.953865
https://doi.org/10.1109/icdar.2001.953865
Publikováno v:
Developments in Applied Artificial Intelligence ISBN: 9783540437819
IEA/AIE
IEA/AIE
In this paper, we propose an approach based on HMM and linguistics for the Vietnamese recognition problem, including handwritten and speech recognition. The main contribution is that our method could be used to model all Vietnamese isolated words by
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::16893eb073c51680f170e7c4fcc9d01f
https://doi.org/10.1007/3-540-48035-8_6
https://doi.org/10.1007/3-540-48035-8_6
Publikováno v:
2014 IEEE International Conference on Image Processing (ICIP); 2014, p838-842, 5p