State-of-the-art person re-identication methods seek robust person matching through combining various feature types. Often, these features are implicitly assigned with a single ve...
Abstract— We propose here to acquire high resolution sequences of a person’s face using a pan-tilt-zoom (PTZ) network camera. This capability should prove helpful in forensic a...
Off-line trained class-specific object detectors are designed to detect any instance of the class in a given image or video sequence. In the context of object tracking, however, o...
We address the problem of learning object class models and object segmentations from unannotated images. We introduce LOCUS (Learning Object Classes with Unsupervised Segmentation...
The major problem in building a good lipreading system is to extract effective visual features from enormous quantity of video sequences data. For appearance-based feature analysi...
Yun Fu, Xi Zhou, Ming Liu, Mark Hasegawa-Johnson, ...