Zobrazeno 1 - 10
of 33 333
pro vyhledávání: '"Saqib ."'
Federated Learning (FL) has emerged as a promising method to collaboratively learn from decentralized and heterogeneous data available at different clients without the requirement of data ever leaving the clients. Recent works on FL have advocated ta
Externí odkaz:
http://arxiv.org/abs/2411.18385
Autor:
Majumder, Al Saqib
Conventional economic and socio-behavioural models assume perfect symmetric access to information and rational behaviour among interacting agents in a social system. However, real-world events and observations appear to contradict such assumptions, l
Externí odkaz:
http://arxiv.org/abs/2411.06011
3D Gaussian Splatting (3DGS) has demonstrated remarkable effectiveness for novel view synthesis (NVS). However, the 3DGS model tends to overfit when trained with sparse posed views, limiting its generalization ability to novel views. In this paper, w
Externí odkaz:
http://arxiv.org/abs/2411.00144
Autor:
Saqib, Danyal, Hussain, Wajahat
Learning Based Robot Grasping currently involves the use of labeled data. This approach has two major disadvantages. Firstly, labeling data for grasp points and angles is a strenuous process, so the dataset remains limited. Secondly, human labeling i
Externí odkaz:
http://arxiv.org/abs/2410.14084
Autor:
Luo, Zhe, Fu, Weina, Liu, Shuai, Anwar, Saeed, Saqib, Muhammad, Bakshi, Sambit, Muhammad, Khan
Action detection and understanding provide the foundation for the generation and interaction of multimedia content. However, existing methods mainly focus on constructing complex relational inference networks, overlooking the judgment of detection ef
Externí odkaz:
http://arxiv.org/abs/2410.05771
Domain Generalization (DG) aims to train models that perform well not only on the training (source) domains but also on novel, unseen target data distributions. A key challenge in DG is preventing overfitting to source domains, which can be mitigated
Externí odkaz:
http://arxiv.org/abs/2410.06020
Autor:
Islam, Md Tanvir, Rahim, Nasir, Anwar, Saeed, Saqib, Muhammad, Bakshi, Sambit, Muhammad, Khan
Publikováno v:
ACM Multimedia 2024
Reducing the atmospheric haze and enhancing image clarity is crucial for computer vision applications. The lack of real-life hazy ground truth images necessitates synthetic datasets, which often lack diverse haze types, impeding effective haze type c
Externí odkaz:
http://arxiv.org/abs/2409.17432
Sonar-based indoor mapping systems have been widely employed in robotics for several decades. While such systems are still the mainstream in underwater and pipe inspection settings, the vulnerability to noise reduced, over time, their general widespr
Externí odkaz:
http://arxiv.org/abs/2409.12094
Publikováno v:
CS & IT - CSCP 2024, Vol. 14, No. 16, pp. 77-94, 2024. ISBN: 978-1-923107-35-9, ISSN: 2231-5403
Cyber-Physical Systems (CPS) integrate physical and embedded systems with information and communication technology systems, monitoring and controlling physical processes with minimal human intervention. The connection to information and communication
Externí odkaz:
http://arxiv.org/abs/2408.16841
Continual learning (CL) addresses the problem of catastrophic forgetting in neural networks, which occurs when a trained model tends to overwrite previously learned information, when presented with a new task. CL aims to instill the lifelong learning
Externí odkaz:
http://arxiv.org/abs/2407.08411