Zobrazeno 1 - 10
of 34 930
pro vyhledávání: '"Meral, A."'
In this work, we propose the first motion transfer approach in diffusion transformer through Mixture of Score Guidance (MSG), a theoretically-grounded framework for motion transfer in diffusion models. Our key theoretical contribution lies in reformu
Externí odkaz:
http://arxiv.org/abs/2412.05355
Text-to-video models have demonstrated impressive capabilities in producing diverse and captivating video content, showcasing a notable advancement in generative AI. However, these models generally lack fine-grained control over motion patterns, limi
Externí odkaz:
http://arxiv.org/abs/2412.05275
Autor:
Elshaar, Mohssen E., khodary, Pansie A., Badr, Meral L., Sayegh, Mohamad A., Manaa, Zeyad M., Abdallah, Ayman M.
This work proposes a strategy for organising quadrotors around a payload to enable hovering without external stimuli, together with a MATLAB software for modelling the dynamics of a quadrotor-payload system. Based on geometric concepts, the proposed
Externí odkaz:
http://arxiv.org/abs/2409.18741
Assessing seismic hazards and thereby designing earthquake-resilient structures or evaluating structural damage that has been incurred after an earthquake are important objectives in earthquake engineering. Both tasks require critical evaluation of s
Externí odkaz:
http://arxiv.org/abs/2408.14962
Autor:
Türkmen, Melek, Meral, Sanem, Yilmaz, Baris, Cikis, Melis, Akagündüz, Erdem, Tileylioglu, Salih
This paper explores the application of deep learning (DL) techniques to strong motion records for single-station epicenter localization. Often underutilized in seismology-related studies, strong motion records offer a potential wealth of information
Externí odkaz:
http://arxiv.org/abs/2405.18451
Low-Rank Adaptations (LoRAs) have emerged as a powerful and popular technique in the field of image generation, offering a highly effective way to adapt and refine pre-trained deep learning models for specific tasks without the need for comprehensive
Externí odkaz:
http://arxiv.org/abs/2403.19776
Publikováno v:
Conditional Information Gain Trellis, Pattern Recognition Letters, Volume 184, 2024, Pages 212-218, ISSN 0167-8655
Conditional computing processes an input using only part of the neural network's computational units. Learning to execute parts of a deep convolutional network by routing individual samples has several advantages: Reducing the computational burden is
Externí odkaz:
http://arxiv.org/abs/2402.08345
Publikováno v:
Asia Pacific Journal of Marketing and Logistics, 2024, Vol. 36, Issue 10, pp. 2689-2705.
Externí odkaz:
http://www.emeraldinsight.com/doi/10.1108/APJML-09-2023-0939
Autor:
Murat Eminoğlu, Gülay, Elçi, Meral
Publikováno v:
Kybernetes, 2023, Vol. 53, Issue 10, pp. 3116-3132.
Externí odkaz:
http://www.emeraldinsight.com/doi/10.1108/K-01-2023-0058
Autor:
Saintives, Camille, Meral, Hélène
Publikováno v:
British Food Journal, 2024, Vol. 126, Issue 11, pp. 3888-3905.
Externí odkaz:
http://www.emeraldinsight.com/doi/10.1108/BFJ-03-2024-0299