Human-nameable visual “attributes” can benefit various recognition tasks. However, existing techniques restrict these properties to categorical labels (for example, a person ...
The latest multi-biometric grand challenge (MBGC 2008) sets up a new experiment in which near infrared (NIR) face videos containing partial faces are used as a probe set and the vi...
The Modeler is designed using a learner-centered approach [5], with scaffolding to address the specific needs of learners. Scaffolding [3] is an educational term that refers to pro...
Many object classes are primarily defined by their functions. However, this fact has been left largely unexploited by visual object categorization or detection systems. We propos...
Abstract. Multiple-instance learning (MIL) allows for training classifiers from ambiguously labeled data. In computer vision, this learning paradigm has been recently used in many ...