Robust Segmentation for Video Captions with Complex Backgrounds.

Zong-Heng Xing Fang Zhou Shu Tian Xu-Cheng Yin

Published in: CCPR (2) (2016)

Keyphrases

robust segmentation
complex background
hand postures
multimedia
video sequences
video data
face detection
video frames
shape prior
foreground objects
lighting conditions
text regions
moving camera
video images
event detection
complex scenes
visual features
image processing