A new AI framework extracts the structural geometry, motifs, and color rules of traditional Weifang kites to support digital cataloging...

A UCLA mathematician has introduced a distance-based representation learning framework grounded in coarse geometry that reads the global shape of...

Researchers at Shenyang University of Technology have developed a distance-aware adaptive graph neural network that estimates 6D object poses from...

Researchers at Shanghai Jiao Tong University have developed an occlusion-aware pairwise relational network that lets robots quickly map which objects...

A comprehensive review shows how machine learning, computer vision, and physics-informed neural networks are transforming microplastic detection, source tracking, and...

A new statistical learning study shows that the apparent benefits of sophisticated multimodal emotion recognition architectures depend critically on independent...

A new spiral-based transformation converts time series into images that let pretrained vision models outperform specialized anomaly detectors across 23...

Researchers in Shanghai have developed TECL, a machine learning framework that treats conflicting opinions across multiple data views as valuable...

Researchers in China have developed a dual-path deep learning network that keeps multimodal sentiment analysis accurate even when text, audio...

A new survey charts the shift in language-guided video segmentation from explicitly described targets to objects that machines must reason...