Zobrazeno 1 - 10
of 486
pro vyhledávání: '"USAMA, Muhammad"'
Autor:
Sinha, Sankalp, Khan, Mohammad Sadil, Usama, Muhammad, Sam, Shino, Stricker, Didier, Ali, Sk Aziz, Afzal, Muhammad Zeshan
Generating high-fidelity 3D content from text prompts remains a significant challenge in computer vision due to the limited size, diversity, and annotation depth of the existing datasets. To address this, we introduce MARVEL-40M+, an extensive datase
Externí odkaz:
http://arxiv.org/abs/2411.17945
Autor:
Ahmad, Muhammad, Butt, Muhammad Hassaan Farooq, Khan, Adil Mehmood, Mazzara, Manuel, Distefano, Salvatore, Usama, Muhammad, Roy, Swalpa Kumar, Chanussot, Jocelyn, Hong, Danfeng
Recent advancements in transformers, specifically self-attention mechanisms, have significantly improved hyperspectral image (HSI) classification. However, these models often suffer from inefficiencies, as their computational complexity scales quadra
Externí odkaz:
http://arxiv.org/abs/2408.01372
Hyperspectral Imaging (HSI) has proven to be a powerful tool for capturing detailed spectral and spatial information across diverse applications. Despite the advancements in Deep Learning (DL) and Transformer architectures for HSI classification, cha
Externí odkaz:
http://arxiv.org/abs/2408.01231
Autor:
Ahmad, Muhammad, Butt, Muhammad Hassaan Farooq, Usama, Muhammad, Altuwaijri, Hamad Ahmed, Mazzara, Manuel, Distefano, Salvatore
Spatial-Spectral Mamba (SSM) improves computational efficiency and captures long-range dependencies, addressing Transformer limitations. However, traditional Mamba models overlook rich spectral information in HSIs and struggle with high dimensionalit
Externí odkaz:
http://arxiv.org/abs/2408.01224
Autor:
Khan, Shahroz, Masood, Zahid, Usama, Muhammad, Kostas, Konstantinos, Kaklis, Panagiotis, Wei, Chen
In this work, we propose a set of physics-informed geometric operators (GOs) to enrich the geometric data provided for training surrogate/discriminative models, dimension reduction, and generative models, typically employed for performance prediction
Externí odkaz:
http://arxiv.org/abs/2407.07611
This paper proposed a straightforward and efficient current control solution for induction machines employing deep symbolic regression (DSR). The proposed DSR-based control design offers a simple yet highly effective approach by creating an optimal c
Externí odkaz:
http://arxiv.org/abs/2405.08277
In this work, we perform a systematic comparison of the effectiveness and efficiency of generative and non-generative models in constructing design spaces for novel and efficient design exploration and shape optimization. We apply these models in the
Externí odkaz:
http://arxiv.org/abs/2402.08540
Autor:
Hyder, Syed Waleed, Usama, Muhammad, Zafar, Anas, Naufil, Muhammad, Fateh, Fawad Javed, Konin, Andrey, Zia, M. Zeeshan, Tran, Quoc-Huy
This paper presents a 2D skeleton-based action segmentation method with applications in fine-grained human activity recognition. In contrast with state-of-the-art methods which directly take sequences of 3D skeleton coordinates as inputs and apply Gr
Externí odkaz:
http://arxiv.org/abs/2309.06462
Autor:
Latif, Siddique, Shoukat, Moazzam, Shamshad, Fahad, Usama, Muhammad, Ren, Yi, Cuayáhuitl, Heriberto, Wang, Wenwu, Zhang, Xulong, Togneri, Roberto, Cambria, Erik, Schuller, Björn W.
This survey paper provides a comprehensive overview of the recent advancements and challenges in applying large language models to the field of audio signal processing. Audio processing, with its diverse signal representations and a wide range of sou
Externí odkaz:
http://arxiv.org/abs/2308.12792
Autor:
Sharmin, Shayla, Usama, Muhammad
Aim: The present study aimed to determine if foreign-born women from different countries of birth have a greater risk of GDM compared to Swedish-born women and to what extent income might mediate this relationship. Methods: This cross-sectional type
Externí odkaz:
http://urn.kb.se/resolve?urn=urn:nbn:se:su:diva-219889