MPT: Multimodal Prompt Tuning for Zero-shot Instruction Learning

T Wang, Y Liu, JC Liang, Y Cui, Y Mao, S Nie… - ar** iterative optimization algorithms into neural networks (NNs), deep unfolding
networks (DUNs) exhibit well-defined and interpretable structures and achieve remarkable …

CPDM: Content-preserving diffusion model for underwater image enhancement

X Shi, YG Wang - Scientific Reports, 2024 - nature.com
Underwater image enhancement (UIE) is challenging since image degradation in aquatic
environments is complicated and changing over time. Existing mainstream methods rely on …

Exploiting multi-transformer encoder with multiple-hypothesis aggregation via diffusion model for 3D human pose estimation

S Arthanari, JH Jeong, YH Joo - Multimedia Tools and Applications, 2024 - Springer
The transformer architecture has consistently achieved cutting-edge performance in the task
of 2D to 3D lifting human pose estimation. Despite advances in transformer-based methods …

MultiSpectral diffusion: joint generation of wavelet coefficients for image synthesis and upsampling

I Goudarzvand, AM Eftekhari Moghadam - Multimedia Tools and …, 2024 - Springer
Diffusion models have become a prevalent framework in deep generative modeling across
various modalities. However, despite producing high quality results, these models are …

Combating deepfakes: a comprehensive multilayer deepfake video detection framework

N Rathoure, RK Pateriya, N Bharot, P Verma - Multimedia Tools and …, 2024 - Springer
Deepfakes represent a class of synthetic media crafted with the aid of advanced deep
learning techniques that exhibit an unparalleled degree of authenticity. The rapid …

LGAST: Towards high-quality arbitrary style transfer with local–global style learning

Z Zhang, Y Li, R **a, M Yang, Y Wang, L Zhao, W **ng - Neurocomputing, 2025 - Elsevier
Arbitrary style transfer has become a research hotspot in academia, industry, and the arts.
While current methods have made great development, but there are still three challenges:(1) …

Content-aware preserving image generation

GH Le, AQ Nguyen, B Kang, Y Lee - Neurocomputing, 2025 - Elsevier
Remarkable progress has been achieved in image generation with the introduction of
generative models. However, precisely controlling the content in generated images remains …