Video temporal segmentation is normally the first and important step for content-based video
applications. Many features including the pixel difference, colour histogram, motion, and …

As most of MPEG and JPEG compression standards are DCT-based, we propose a simple,
low-cost and fast algorithm to extract dominant colour features directly in DCT domain …

Generative learning in pixel domain has achieved great success in exploiting their
correlations in processing images towards desired objectives, yet learning in frequency …

In the field of shot boundary detection the fundamental step is video content analysis
towards video indexing, summarization and retrieval as to be carried out for video cloud …

Pixel‐based generative image inpainting has been widely researched over recent years and
certain level of success via deep learning of feature representations and hallucinations of …

A DCT domain analysis of facial images is reported, which reveals that, when a certain
number of DCT coefficients are removed the corresponding facial image description by the …

In this short article, we introduce a new concept in HERMES, the FP7 funded project in
Europe, in developing technology innovations towards computer aided memory …

This paper proposes a thorough scheme, by virtue of camera zooming descriptor with two-
level threshold, to automatically retrieve close-ups directly from moving picture experts …

In this article, we introduce a new concept in HERMES, the FP7 funded project in Europe, in
developing technology innovations towards computer aided memory management via …

Progressive content access provides a mode that allows a coarse version of an image being
viewed at a lower computing cost and then gradually refined by subsequent resolution …