This paper proposes a method of automated individualization of eye region model. The eye region model has been proposed in past research that parameterizes both the structure and ...
Camera networks are being deployed for various applications like security and surveillance, disaster response and environmental modeling. However, there is little automated process...
Bi Song, Ahmed T. Kamal, Cristian Soto, Chong Ding...
Discriminative methods for visual object category recognition are typically non-probabilistic, predicting class labels but not directly providing an estimate of uncertainty. Gauss...
Ashish Kapoor, Kristen Grauman, Raquel Urtasun, Tr...
This paper presents a framework for robustly recognizing physical team behaviors by exploiting spatio-temporal patterns. Agent team behaviors in athletic and military domains typi...
This paper presents a scalable solution to the problem of tracking objects across spatially separated, uncalibrated, non-overlapping cameras. Unlike other approaches this technique...