A semantically meaningful image hierarchy can ease the human effort in organizing thousands and millions of pictures (e.g., personal albums), and help to improve performance of en...
Li-Jia Li, Chong Wang, Yongwhan Lim, David Blei, L...
How can knowing about some categories help us to discover new ones in unlabeled images? Unsupervised visual category discovery is useful to mine for recurring objects without huma...
When classifying high-dimensional sequence data, traditional methods (e.g., HMMs, CRFs) may require large amounts of training data to avoid overfitting. In such cases dimensional...
Image matching has been a central research topic in computer vision over the last decades. Typical approaches to correspondence involve matching features between images. In this pa...
Since the large diffusion of digital camera and mobile devices with embedded camera and flashgun, the red-eyes artifacts have de-facto become a critical problem. The technique he...
Sebastiano Battiato, Giovanni Maria Farinella, Mir...