IEEE Transactions on Pattern Analysis and Machine Intelligence

News

26 Dec 2023
- Professor Sunghoon Im's team at DGIST has developed depth-sensing technology that can be reliably used in diverse environments by analyzing the relationship between the neural network structure and distance sensing in autonomous driving. - The new technology is expected to contribute to the development of a wide range of AI fields, such as autonomous driving, which must be performed safely in various urban settings and weather conditions
A process of continual learning for a synthetic multi-label dataset
31 Jan 2023
A research group at the Osaka Metropolitan University Graduate School of Informatics has developed a new learning method for artificial intelligence that combines classification performance for data with multiple labels with the ability to learn continually from data. Numerical experiments on real-world multi-label data indicate that the new method outperforms conventional approaches. The simplicity of this algorithm makes it easy to integrate it with other algorithms to devise new ones.
06 Mar 2020
Point set registration problems, i.e. finding corresponding points between shapes represented as point sets, are important in a variety of fields, so algorithms have been developed. Here, a new algorithm is discovered for point set registration problems. This algorithm is demonstrated to solve several typical problems remarkably faster than conventional methods and with the highest accuracy. This novel algorithm will be beneficial to a wide variety of technologies including computer graphics, computer vision, authentication etc.