Human-nameable visual attributes offer many advantages when used as mid-level features for object recognition, but existing techniques to gather relevant attributes can be ineffici...
—Urban sensing where mobile users continuously gather, process, and share location-sensitive sensor data (e.g., street images, road condition, traffic flow) is emerging as a ne...
We develop a system for 3D object retrieval based on sketched feature lines as input. For objective evaluation, we collect a large number of query sketches from human users that a...
Mathias Eitz, Ronald Richter, Tamy Boubekeur, Kris...
Background: Modelling the ligand binding site of a protein is an important component of understanding proteinligand interactions and is being actively studied. Even if the side ch...
Subspace learning techniques are widespread in pattern recognition research. They include PCA, ICA, LPP, etc. These techniques are generally linear and unsupervised. The problem o...