Accurate and efficient portrait instance segmentation has become a crucial enabler for many
multimedia applications on mobile devices. We present a novel convolutional neural …

Despite the remarkable progress of semantic segmentation in recent years, much remains to
be addressed in order to achieve better semantic coherence and boundary delineation. In …

Convolutional neural networks (CNN) have made significant advances in hyperspectral
image (HSI) classification. However, standard convolutional kernel neglects the intrinsic …

Convolutional neural networks (CNN) have made significant advances in detecting roads
from satellite images. However, existing CNN approaches are generally repurposed …

Convolutional neural networks (CNNs) have achieved remarkable performance in
hyperspectral image (HSI) classification over the last few years. Despite the progress that …

In this paper, we propose a novel approach to learning semantic contextual relationships in
videos for semantic object segmentation. Our algorithm derives the semantic contexts from …

Human body parsing remains a challenging problem in natural scenes due to multi-instance
and inter-part semantic confusions as well as occlusions. This paper proposes a novel …

We propose a novel approach for modeling semantic contextual relationships in videos. This
graph-based model enables the learning and propagation of higher-level spatial-temporal …

In this paper, we propose a user density estimation system using high frequencies and the
microphone of a smart device in a specific closed space. High frequencies are sent to the …