A practical lipreading system can be considered either as subject dependent (SD) or subject-independent (SI). An SD system is user-specific, i.e., customized for some particular ...
The bounding box representation employed by many popular object detection models [3, 6] implicitly assumes all pixels inside the box belong to the object. This assumption makes th...
Recognizing faces in unconstrained videos is a task of mounting importance. While obviously related to face recognition in still images, it has its own unique characteristics and ...
Active learning and crowdsourcing are promising ways to efficiently build up training sets for object recognition, but thus far techniques are tested in artificially controlled ...
This paper presents a new method for viewpoint invariant pedestrian recognition problem. We use a metric learning framework to obtain a robust metric for large margin nearest neigh...
Mert Dikmen, Emre Akbas, Thomas S. Huang, Narendra...