Titlebook: Intelligence Science and Big Data Engineering. Visual Data Engineering; 9th International Co Zhen Cui,Jinshan Pan,Jian Yang Conference proc

哀求

施舍

Adaptive Online Learning for Video Object Segmentation,y an annotated first frame. Previous VOS methods based on deep neural networks often solves this problem by fine-tuning the segmentation model in the first frame of the test video sequence, which is time-consuming and can not be well adapted to the current target video. In this paper, we proposed th

懒洋洋

Proposal-Aware Visual Saliency Detection with Semantic Attention,ention mechanism, semantic attention (SeA). The attention are established based on the observation that regions with high attention should have similarly semantic concepts with salient objects. The SeA takes the high-level semantic features from Faster Region-based Convolutional Neural Network (Fast

使害怕

Constrainted Subspace Low-Rank Representation with Spatial-Spectral Total Variation for Hyperspectre separated into different classification based on the land-covers, which means the spectral space can be regarded as an union of several low-rank subspaces. Subspace low-rank representation (SLRR) is a powerful tool in exploring the inner low-rank structure of spectral space and has been applied fo

侵蚀

leniency

Egomotion Estimation Under Planar Motion with an RGB-D Camera,als with the corridor-like structured scenarios and uses the prior knowledge of the environment: when at least one vertical plane is detected using the depth data, egomotion is estimated with one normal of the vertical plane and one point; when there are no vertical planes, a 2-point homography-base

Cirrhosis

Sparse-Temporal Segment Network for Action Recognition,work, the sparse-temporal segment network to recognize human actions is proposed. Considering the sparse features contains the information of moving objects in videos, for example marginal information which is helpful to capture the target region and reduce the interference from similar actions, the

floaters

murmur

Deep Blind Image Inpainting,ume that the positions of the corrupted regions are known. Different from existing methods that usually make some assumptions on the corrupted regions, we present an efficient blind image inpainting algorithm to directly restore a clear image from a corrupted input. Our algorithm is motivated by the

抛射物