Zobrazeno 1 - 10
of 110
pro vyhledávání: '"Das, Abir"'
Recognizing actions from a limited set of labeled videos remains a challenge as annotating visual data is not only tedious but also can be expensive due to classified nature. Moreover, handling spatio-temporal data using deep $3$D transformers for th
Externí odkaz:
http://arxiv.org/abs/2409.02910
Intent Management Function (IMF) is an integral part of future-generation networks. In recent years, there has been some work on AI-based IMFs that can handle conflicting intents and prioritize the global objective based on apriori definition of the
Externí odkaz:
http://arxiv.org/abs/2405.07621
Continual Learning (CL) enables machine learning models to learn from continuously shifting new training data in absence of data from old tasks. Recently, pretrained vision transformers combined with prompt tuning have shown promise for overcoming ca
Externí odkaz:
http://arxiv.org/abs/2403.20317
Intent-based management will play a critical role in achieving customers' expectations in the next-generation mobile networks. Traditional methods cannot perform efficient resource management since they tend to handle each expectation independently.
Externí odkaz:
http://arxiv.org/abs/2310.17416
Autor:
Roy, Anurag, Verma, Vinay Kumar, Voonna, Sravan, Ghosh, Kripabandhu, Ghosh, Saptarshi, Das, Abir
Continual Learning (CL) involves training a machine learning model in a sequential manner to learn new information while retaining previously learned tasks without the presence of previous training data. Although there has been significant interest i
Externí odkaz:
http://arxiv.org/abs/2308.11357
Publikováno v:
2023 IEEE 9th International Conference on Network Softwarization (NetSoft)
The dynamic and evolutionary nature of service requirements in wireless networks has motivated the telecom industry to consider intelligent self-adapting Reinforcement Learning (RL) agents for controlling the growing portfolio of network services. In
Externí odkaz:
http://arxiv.org/abs/2303.01013
Autor:
Gupta, Santanu1 (AUTHOR), Das, Abir2 (AUTHOR), Ganguli, Kuhely1 (AUTHOR), Chakraborty, Nilakshi2 (AUTHOR), Fayezizadeh, Mohammad Reza3 (AUTHOR) rfayezi@yahoo.com, Sil, Sudipta Kumar4 (AUTHOR) sudiptakrsil@gmail.com, Adak, Malay Kumar2 (AUTHOR), Hasanuzzaman, Mirza5,6 (AUTHOR) mhzsauag@yahoo.com
Publikováno v:
Scientific Reports. 10/19/2024, Vol. 14 Issue 1, p1-19. 19p.
Generating natural language questions from visual scenes, known as Visual Question Generation (VQG), has been explored in the recent past where large amounts of meticulously labeled data provide the training corpus. However, in practice, it is not un
Externí odkaz:
http://arxiv.org/abs/2210.07076
Deep Learning has become overly complicated and has enjoyed stellar success in solving several classical problems like image classification, object detection, etc. Several methods for explaining these decisions have been proposed. Black-box methods t
Externí odkaz:
http://arxiv.org/abs/2111.13406
Unsupervised domain adaptation which aims to adapt models trained on a labeled source domain to a completely unlabeled target domain has attracted much attention in recent years. While many domain adaptation techniques have been proposed for images,
Externí odkaz:
http://arxiv.org/abs/2110.15128