ScienceT2I: Enhancing Scientific Accuracy in Image Synthesis
Discover how ScienceT2I improves scientific accuracy in image synthesis with advanced datasets, SciScore, and alignment frameworks for better model perform...
Blind Users’ Preferences for Vision-Language Scene Descriptions
Explore how blind and low-vision individuals prefer large vision-language model-generated scene descriptions to improve navigation and reduce anxiety.
Boost Team Diversity with Generative AI in Project Management
Discover how Generative AI enhances team diversity and dynamics with a novel project management framework for better innovation and success.
Robust Cross-Camera Distracted Driver Detection Model
Discover DBMNet, a lightweight model using feature disentanglement and contrastive learning for accurate distracted driver detection across cameras.
Divide-and-Conquer Side-Channel Attacks on DNN Models
Discover a novel divide-and-conquer strategy for extracting deep neural networks via side-channel attacks with high fidelity and accuracy.