Abstract. We propose a novel unsupervised transfer learning framework that utilises unlabelled auxiliary data to quantify and select the most relevant transferrable knowledge for r...
Abstract--We present a novel tracking method for effectively tracking objects in structured environments. The tracking method finds applications in security surveillance, traffic m...
Abstract—Contour features play an important role in object recognition. Psychological experiments have shown that maximum-curvature points are most distinctive along a contour [6...
Recent computer vision approaches are aimed at richer image interpretations that extend the standard recognition of objects in images (e.g., cars) to also recognize object attribu...
William Curran, Travis Moore, Todd Kulesza, Weng-K...
Abstract. We present a novel video retrieval system that accepts annotated freehand sketches as queries. Existing sketch based video retrieval (SBVR) systems enable the appearance ...