IEEE

DCFormer: Divide-and-Conquer in 3D Human Pose Estimation Tasks

Abstract: Monocular 3D human pose estimation based on Transformer has recently attracted significant attention. Intuitively, general 3D human pose estimation simultaneously learns the camera ...

The hottest Stanford computer science class isn't banning AI tools — it's embracing them

One of the hottest Stanford CS courses this semester embraces rather than bans AI coding tools like Cursor and Claude.

When computers took over the factory floor: Economist traces how workers adapted, what it means for AI's future

In the early 1970s, a quiet revolution began in American factories. Lathes, drill presses and milling machines—once guided by ...
IEEE

Relationship-Incremental Scene Graph Generation by a Divide-and-Conquer Pipeline With Feature Adapter

Abstract: As a challenging computer vision task, Scene Graph Generation (SGG) finds the latent semantic relationships among objects from a given image, which may be limited by the datasets and ...