A good training dataset, representative of the test images expected in a given application, is critical for ensuring good performance of a visual categorization system. Obtaining ...
Aniruddha Kembhavi, Behjat Siddiquie, Roland Miezi...
We propose a novel probabilistic framework for learning
visual models of 3D object categories by combining appearance
information and geometric constraints. Objects are
represen...
A multidisciplinary team at Philips Sound and Vision's TV Lab developed an E-mail-on-TV functionality. Their objective is to offer the benefits of E-mail to people in their l...
Identifying verbally and non-verbally referred-to objects is an important aspect of human-robot interaction. Most importantly, it is essential to achieve a joint focus of attentio...
We propose using the proximity distribution of vectorquantized local feature descriptors for object and category recognition. To this end, we introduce a novel "proximity dis...