Results 311 to 320 of about 6,403,045 (365)

A competition-based image saliency model

SPIE/COS Photonics Asia, 2019
Competition for visual representation is an important mechanism for selective visual attention. The traditional global distinctiveness based saliency models usually compute the distinctiveness to measure saliency via comparing the difference of image ...
Yang Li, X. Mou
semanticscholar   +1 more source

Going from Image to Video Saliency: Augmenting Image Salience with Dynamic Attentional Push

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018
We present a novel method to incorporate the recent advent in static saliency models to predict the saliency in videos. Our model augments the static saliency models with the Attentional Push effect of the photographer and the scene actors in a shared attention setting.
Siavash Gorji, James J. Clark
openaire   +1 more source

RSF: A Novel Saliency Fusion Framework for Image Saliency Detection

2020 International Conference on Culture-oriented Science & Technology (ICCST), 2020
Image saliency detection has become a hot topic in computer vision tasks. A large number of saliency models have been developed in recent years. Considering that these models use different prior knowledge, features, and theoretical methods, they have their own strengths and weaknesses in different images.
Yunhe Wu, Tong Jia, Wenhao Li, Dongyue Chen   +3 more
openaire   +1 more source

Stage-wise Salient Object Detection in 360° Omnidirectional Image via Object-level Semantical Saliency Ranking

IEEE Transactions on Visualization and Computer Graphics, 2020
The 2D image based salient object detection (SOD) has been extensively explored, while the 360° omnidirectional image based SOD has received less research attention and there exist three major bottlenecks that are limiting its performance.
Guangxiao Ma, Shuai Li, Chenglizhao Chen, A. Hao, Hong Qin   +4 more
semanticscholar   +1 more source

Image structure-based saliency detection

Journal of Electronic Imaging, 2017
We consider image intrinsic structure in two aspects: foreground saliency computation and background saliency calculation. On the one hand, a segmented image is represented as a weighted undirected graph, and we calculate the foreground saliency by choosing some superpixels as ranking queries, where we apply a robust background measure to select those ...
Weidong Zhao, Xianhui Liu, Yufei Chen, Jing Hong   +3 more
openaire   +1 more source

Saliency-based stereoscopic image retargeting

Information Sciences, 2016
Abstract In this paper, we propose a new saliency based stereoscopic image retargeting method based on the characteristics of the Human Visual System (HVS). A new stereoscopic saliency detection method is designed by adopting low-level features of intensity, color, texture and depth.
Fang, Yuming, Wang, Junle, Yuan, Yuan, Lei, Jianjun, Le Callet, Patrick, Lin, Weisi   +5 more
openaire   +2 more sources

Re-Caption: Saliency-Enhanced Image Captioning Through Two-Phase Learning

IEEE Transactions on Image Processing, 2020
Visual saliency and semantic saliency are important in image captioning. However, a single-phase image captioning model benefits little from limited saliency information without a saliency predictor. In this paper, a novel saliency-enhanced re-captioning
Lian Zhou, Yuejie Zhang, Yu-Gang Jiang, Tao Zhang, Weiguo Fan   +4 more
semanticscholar   +1 more source

Saliency guided image-driven simplification

2011 8th International Conference on Information, Communications & Signal Processing, 2011
Image-driven simplification has been proposed as a simplification method which generates models with high visual fidelity and factors in the error from mesh appearance properties. We propose to enhance it by improving the preservation of important regions of the simplified mesh.
null Cheen-Hau Tan, null Lap-Pui Chau
openaire   +1 more source

Saliency detection for RGBD images

Proceedings of the 7th International Conference on Internet Multimedia Computing and Service, 2015
Additional depth information from RGBD images is one of characteristics different from conventional 2D images. In this paper, we propose an effective saliency model to detect salient regions in RGBD images. Color contrast and depth contrast are first enhanced with the weighting of depth-based object probability.
Hangke Song, Zhi Liu, Huan Du, Guangling Sun, Cong Bai   +4 more
openaire   +1 more source

SALIENCY-BASED UNSUPERVISED IMAGE MATTING

International Journal of Pattern Recognition and Artificial Intelligence, 2014
Spectral matting is the state-of-the-art matting method and can well solve the highly under-conditioned matte problem without manual intervention. However, it suffers from huge computation cost and inaccurate alpha matte. This paper presents a modified spectral matting method which combines saliency detection algorithm to get a higher accuracy of ...
GUANGHUA TAN, JUN QI, CHUNMING GAO, JIN CHEN, LIYUAN ZHUO   +4 more
openaire   +1 more source