Filters








6,813 Hits in 4.8 sec

Co-saliency Detection Linearly Combining Single-View Saliency and Foreground Correspondence

Huiyun JING, Xin HE, Qi HAN, Xiamu NIU
2015 IEICE transactions on information and systems  
Then the foreground correspondence is linearly combined with single-view saliency to compute co-saliency.  ...  The research of detecting co-saliency over multiple images is just beginning.  ...  matching: Since the progressive graph matching approach is robust to the in-class variations of co-salient object, we utilize progressive graph matching between the multiple estimated image foreground  ... 
doi:10.1587/transinf.2014edl8172 fatcat:oy27aqoixjgc7civxnurvvhetq

Image co-saliency detection by propagating superpixel affinities

Zhiyu Tan, Liang Wan, Wei Feng, Chi-Man Pun
2013 2013 IEEE International Conference on Acoustics, Speech and Signal Processing  
Bipartite graph matching is applied to determine most reliable inter similarities.  ...  Image co-saliency detection is a valuable technique to highlight perceptually salient regions in image pairs.  ...  By this way, we actually convert co-saliency detection problem to saliency detection. One notable advantage is that we can adapt successful single-image saliency techniques for co-saliency detection.  ... 
doi:10.1109/icassp.2013.6638027 dblp:conf/icassp/TanWFP13 fatcat:vzvggi5inzd5bavj5w54z5hlzu

A Co-Saliency Model of Image Pairs

Hongliang Li, King Ngi Ngan
2011 IEEE Transactions on Image Processing  
local attention » Using three saliency detection techniques • Multi-Image Saliency Map (MISM) − Using co-multilayer pyramid − Describing each node in graph » two types of visual descriptor (color and texture  ...   Goal of proposed method -Detecting co-saliency from image pair • Extracting similar objects from image pair  Proposed method -Using co-saliency model • Single-Image Saliency Map (SISM) − Describing  ...  • Designing co-multilayer graph   ,    G V E with nodes v V and edges e E Fig. 3.  ... 
doi:10.1109/tip.2011.2156803 pmid:21606024 fatcat:y6gbv6tairey5kp3aggst6pgvy

Co-Salient Object Detection Based on Deep Saliency Networks and Seed Propagation Over an Integrated Graph

Dong-ju Jeong, Insung Hwang, Nam Ik Cho
2018 IEEE Transactions on Image Processing  
In addition, the integrated multilayer graph is constructed to find the regions that the previous steps may not detect by seed propagation with low-level descriptors.  ...  Our experiments have demonstrated that the proposed approach outperforms comparable co-saliency detection methods on widely used public databases and can also be directly applied to co-segmentation tasks  ...  The Integrated Graph with a Cluster Layer In [27] , the bipartite graph matching method finds pairs of the most relevant superpixels between two images, each of which is connected with its matching score  ... 
doi:10.1109/tip.2018.2859752 pmid:30047881 fatcat:odimamhty5ax7pg5zftsqga4kq

Salient object cutout using Google images

Hongyuan Zhu, Jianfei Cai, Jianmin Zheng, Jianxin Wu, Nadia Thalmann
2013 2013 IEEE International Symposium on Circuits and Systems (ISCAS2013)  
Then, the enhanced saliency map is used to initialize the graph-cut to extract the object-of-interest.  ...  Saliency detection techniques are able to provide some rough information about object-of-interest since they highlight high-contrast or high attention regions or pixels.  ...  We would like to point out that our internet assisted image segmentation is different from the co-segmentation problem [9] , [10] or the co-saliency detection problem [11] , [10] .  ... 
doi:10.1109/iscas.2013.6571994 dblp:conf/iscas/ZhuCZWM13 fatcat:jzmrtdtgvfdb7oljk7gc5gwh7m

Co-Salient Object Detection From Multiple Images

Hongliang Li, Fanman Meng, King Ngi Ngan
2013 IEEE transactions on multimedia  
In this paper, we propose a novel method to discover co-salient objects from a group of images, which is modeled as a linear fusion of an intra-image saliency (IaIS) map and an inter-image saliency (IrIS  ...  Experimental evaluation on a number of images demonstrates the good performance of the proposed method on co-salient object detection.  ...  Based on (7), we measure the co-saliency of a region in the region group by (9) From (9) , we can see that the region matching is only performed on the image pairs with edge links in MST graph. 4)  ... 
doi:10.1109/tmm.2013.2271476 fatcat:3jgyjnue2ra65ggcsaiym6dvn4

Co-Saliency Detection for RGBD Images Based on Multi-Constraint Feature Matching and Cross Label Propagation

Runmin Cong, Jianjun Lei, Huazhu Fu, Qingming Huang, Xiaochun Cao, Chunping Hou
2018 IEEE Transactions on Image Processing  
The proposed method introduces the depth information and multi-constraint feature matching to improve the performance of co-saliency detection.  ...  Different from the most existing co-saliency methods focusing on RGB images, this paper proposes a novel co-saliency detection model for RGBD images, which utilizes the depth information to enhance identification  ...  In [50] , the multiscale segmentation voting based intra saliency map is integrated with image pairwise matching based inter saliency map for co-saliency detection.  ... 
doi:10.1109/tip.2017.2763819 pmid:29053455 fatcat:yok5suowh5ga5dx3mkvhinmkda

Adaptive Graph Convolutional Network with Attention Graph Clustering for Co-saliency Detection [article]

Kaihua Zhang, Tengpeng Li, Shiwen Shen, Bo Liu, Jin Chen, Qingshan Liu
2020 arXiv   pre-print
Third, we present a unified framework with encoder-decoder structure to jointly train and optimize the graph convolutional network, attention graph cluster, and co-saliency detection decoder in an end-to-end  ...  Co-saliency detection aims to discover the common and salient foregrounds from a group of relevant images.  ...  to the co-saliency detection task compared with the fixed graph design in the vanilla GCNs [30] .  ... 
arXiv:2003.06167v1 fatcat:viapz273g5cv7lzln7x76pfuxq

Image Co-Segmentation and Efficiency Saliency Detection

K. Prasanth
2018 International Journal for Research in Applied Science and Engineering Technology  
A region-based likelihood estimation procedure is first performed to provide the prior knowledge for our higher order energy function.Further extended the work for image saliency detection which is used  ...  There is no co-saliency method that makes useof depth cues.Compared with the enormous amount of work on 2-D imagesaliency estimation, saliency detection for 3-D images is a farless touched topic.  ...  labeled images T, we first build a globalterm Eglobal{ , … … … , } to match all the images with thelabeled images T.  ... 
doi:10.22214/ijraset.2018.4109 fatcat:iyljvan5pvc6jnvjy3fwn63tlm

Improved Segmentation of Suspicious Regions of Masses in Mammograms by Watershed Transform

P.V. Anuradha, Babita Roslind Jose, Jimson Mathew
2015 Procedia Computer Science  
The suspicious mass regions are isolated and the results are compared with two current methods: thresholding of graph based saliency map of preprocessed mammogram and morphological extraction from saliency  ...  Screening mammograms are powerful aids in early detection of breast cancer. This work deals with segmentation of suspicious region of anomalies known as masses in mammogram.  ...  Graph based visual saliency (GBVS) computes saliency of a region with respect to its local neighbourhood using the directional contrast.  ... 
doi:10.1016/j.procs.2015.02.068 fatcat:ohvtxvmkcvhc5baei7rk7pr6ua

Review of Visual Saliency Detection with Comprehensive Information [article]

Runmin Cong, Jianjun Lei, Huazhu Fu, Ming-Ming Cheng, Weisi Lin, and Qingming Huang
2018 arXiv   pre-print
RGBD saliency detection, co-saliency detection, or video saliency detection.  ...  Co-saliency detection model introduces the inter-image correspondence constraint to discover the common salient object in an image group.  ...  [74] proposed a self-contained co-saliency detection model based on affinity matrix, which evaluates the co-saliency according to the bipartite superpixel-level graph matching across image pairs.  ... 
arXiv:1803.03391v2 fatcat:htcmhlo32jhczehvvq6nmgzwam

Video Co-segmentation for Meaningful Action Extraction

Jiaming Guo, Zhuwen Li, Loong-Fah Cheong, Steven Zhiying Zhou
2013 2013 IEEE International Conference on Computer Vision  
We further leverage the graph matching to enforce geometric coherence between regions so as to reduce feature ambiguity and matching errors.  ...  Finally, to classify the trajectories into common action and action outliers, we formulate the problem as a binary labeling of a Markov Random Field, in which the data term is measured by the trajectory co-saliency  ...  Co-Saliency Measurement With the matching scores of all inter-video cluster pairs at our disposal, we can now compute the co-saliency of a trajectory in F a w.r.t F b as follows: Mt(tr i a , F b ) = max  ... 
doi:10.1109/iccv.2013.278 dblp:conf/iccv/GuoLCZ13 fatcat:d2n2qmdh6rexxnrgv4xdhbcuzq

Unsupervised Object Discovery for Instance Recognition

Oriane Simeoni, Ahmet Iscen, Giorgos Tolias, Yannis Avrithis, Ondrej Chum
2018 2018 IEEE Winter Conference on Applications of Computer Vision (WACV)  
Saliency is based on a centrality measure of a nearest neighbor graph constructed from regional CNN representations of dataset images.  ...  In this work, we propose a novel salient region detection method. It captures, in an unsupervised manner, patterns that are both discriminative and common in the dataset.  ...  Representative cases are common object discovery [41, 38] , co-occurrence detection [6] , or methods using GPS information [8, 20] .  ... 
doi:10.1109/wacv.2018.00194 dblp:conf/wacv/SimeoniITAC18 fatcat:yqdibyg5tbdxnepmeuamtq2y6e

Unsupervised object discovery for instance recognition [article]

Oriane Siméoni and Ahmet Iscen and Giorgos Tolias and Yannis Avrithis and Ondrej Chum
2018 arXiv   pre-print
Saliency is based on a centrality measure of a nearest neighbor graph constructed from regional CNN representations of dataset images.  ...  In this work, we propose a novel salient region detection method. It captures, in an unsupervised manner, patterns that are both discriminative and common in the dataset.  ...  Representative cases are common object discovery [41, 38] , co-occurrence detection [6] , or methods using GPS information [8, 20] .  ... 
arXiv:1709.04725v2 fatcat:rxekvxo6cfc3xbwfoyuq5wi7ha

A Survey of Object Co-segmentation

Zhoumin Lu, Haiping Xu, Genggeng Liu
2019 IEEE Access  
This paper reviews some classic and effective object co-segmentation methods, including saliency-based approaches, joint-processing-based approaches, graph-based approaches, and others.  ...  INDEX TERMS Computer vision, semantic segmentation, object co-segmentation, joint processing, saliency, model evaluation.  ...  We accepted them with humility and the paper has been considerably improved. We also express sincere gratitude. Finally, we are also grateful to the editors responsible for this paper.  ... 
doi:10.1109/access.2019.2917152 fatcat:qipvlujtnraqfbfnjhk7q4eawq
« Previous Showing results 1 — 15 out of 6,813 results