Filters








123 Hits in 4.1 sec

An Iterative Co-Saliency Framework for RGBD Images [article]

Runmin Cong, Jianjun Lei, Huazhu Fu, Weisi Lin, Qingming Huang, Xiaochun Cao, Chunping Hou
2017 arXiv   pre-print
In this paper, we propose an iterative RGBD co-saliency framework, which utilizes the existing single saliency maps as the initialization, and generates the final RGBD cosaliency map by using a refinement-cycle  ...  Moreover, they mainly focus on RGB image and ignore the depth information for RGBD images.  ...  The major contributions of the proposed method are: 1) An iterative co-saliency framework for RGBD images is proposed, which integrates addition scheme, deletion scheme, and iteration scheme.  ... 
arXiv:1711.01371v1 fatcat:wimzz4snhfbermowwqacdlq3ta

Object-based RGBD image co-segmentation with mutex constraint

Huazhu Fu, Dong Xu, Stephen Lin, Jiang Liu
2015 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
Experiments show that this object-based RGBD co-segmentation with mutex constraints outperforms related techniques on an RGBD co-segmentation dataset, while effectively processing noisy images.  ...  With RGBD images, our method utilizes the depth channel to enhance identification of similar foreground objects via a proposed RGBD co-saliency map, as well as to improve detection of object-like regions  ...  In our work, we take advantage of both approaches to combine the depth and co-saliency cues from multiple RGBD images by integrating them within the saliency map fusion framework of [6] .  ... 
doi:10.1109/cvpr.2015.7299072 dblp:conf/cvpr/FuXLL15 fatcat:zgjo3xduorfpnogw7ottkj2doe

HSCS: Hierarchical Sparsity Based Co-saliency Detection for RGBD Images [article]

Runmin Cong, Jianjun Lei, Huazhu Fu, Qingming Huang, Xiaochun Cao, and Nam Ling
2018 arXiv   pre-print
In this paper, we propose a novel co-saliency detection method for RGBD images based on hierarchical sparsity reconstruction and energy function refinement.  ...  Co-saliency detection aims to discover common and salient objects in an image group containing more than two relevant images.  ...  In [68] , an iterative co-saliency detection framework for RGBD images is proposed, which integrates the addition scheme, deletion scheme, and iterative scheme.  ... 
arXiv:1811.06679v1 fatcat:k54zbjluafclvgsjpmqgllnjmq

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
Co-saliency detection model introduces the inter-image correspondence constraint to discover the common salient object in an image group.  ...  RGBD saliency detection, co-saliency detection, or video saliency detection.  ...  In [92] , an iterative co-saliency detection framework for RGBD images was proposed, which integrates the addition scheme, deletion scheme, and iterative scheme.  ... 
arXiv:1803.03391v2 fatcat:htcmhlo32jhczehvvq6nmgzwam

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  
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  ...  Co-saliency detection aims at extracting the common salient regions from an image group containing two or more relevant images. It is a newly emerging topic in computer vision community.  ...  However, little work has been done on co-saliency detection for RGBD images.  ... 
doi:10.1109/tip.2017.2763819 pmid:29053455 fatcat:yok5suowh5ga5dx3mkvhinmkda

A Dense Map Building Approach from Spherical RGBD Images
english

Tawsif Gokhool, Maxime Meilland, Patrick Rives, Eduardo Fernández-Moral
2014 Proceedings of the 9th International Conference on Computer Vision Theory and Applications  
Both methods are evaluated with data acquired with a recently proposed omnidirectional RGBD sensor for indoor environments.  ...  In this work, we first propose to tackle the pose estimation problem by using both photometric and geometric information in a direct RGBD image registration method.  ...  CONCLUSIONS In this paper, a spherical RGBD registration method has been proposed and we have demonstrated that both photometry and geometry can co-exist within the same framework.  ... 
doi:10.5220/0004745406560663 dblp:conf/visapp/GokhoolMRF14 fatcat:q5hsxo6inrdhrfkygkso3v3ftq

Grey Wolf Optimization on Modeling Saliency Detection in Stereoscopic 3D Images

2019 International journal of recent technology and engineering  
Anyhow, specific appliances of stereoscopic imaging require improvements in saliency detection schemes for extracting the salient regions in a precise manner.  ...  The saliency detection (SD) model faces numerous shortcomings like intricacy in natural images and minor-scale patterns on salient objects.  ...  The saliency value f i S of i image patch from f features is devised as per Eq. (1), in which   depth F TE CO CO LU f , , , , 2   f ij k i j f i H e S ij 2 2 2 / 2 1       (1) The evaluation  ... 
doi:10.35940/ijrte.b1191.0782s419 fatcat:tiveap4nqjexjnqhbl2oswrp3e

Recent Advances in Saliency Estimation for Omnidirectional Images, Image Groups, and Video Sequences

Marco Buzzelli
2020 Applied Sciences  
for co-saliency, and saliency shift for video saliency estimation.  ...  We focus on domains that are especially recent and relevant, as they make saliency estimation particularly useful and/or effective: omnidirectional images, image groups for co-saliency, and video sequences  ...  [95] presented FASS: a feature-adaptive semi-supervised framework for co-saliency estimation.  ... 
doi:10.3390/app10155143 fatcat:3akkibaelnfnpav2x7gfdllhg4

Grounded Affordance from Exocentric View [article]

Hongchen Luo, Wei Zhai, Jing Zhang, Yang Cao, Dacheng Tao
2022 arXiv   pre-print
In addition, an affordance grounding dataset named AGD20K is constructed by collecting and labeling over 20K images from 36 affordance categories.  ...  Specifically, the perception of affordance regions is enhanced by preserving affordance co-relations.  ...  For saliency detection models, we use models trained on the saliency datasets and test in the same way as [3].  ... 
arXiv:2208.13196v1 fatcat:4lyaf2upkjegjep3dixo3k54g4

UC-Net: Uncertainty Inspired RGB-D Saliency Detection via Conditional Variational Autoencoders

Jing Zhang, Deng-Ping Fan, Yuchao Dai, Saeed Anwar, Fatemeh Sadat Saleh, Tong Zhang, Nick Barnes
2020 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
saliency maps for each input image by sampling in the latent space.  ...  In this paper, we propose the first framework (UC-Net) to employ uncertainty for RGB-D saliency detection by learning from the data labeling process.  ...  We thank all reviewers and Area Chairs for their constructive comments.  ... 
doi:10.1109/cvpr42600.2020.00861 dblp:conf/cvpr/ZhangFDASZB20 fatcat:wokbwmp6jzddzlh2k2sfwc6wia

Salient Object Detection: An Accurate and Efficient Method for Complex Shape Objects

Min Qiao, Gang Zhou, Qiu Ling Liu, Li Zhang
2021 IEEE Access  
Additionally, our method achieves excellent detection results for objects with complex shapes.  ...  To obtain an accurate edge, an edge profile enhancement module (EPEM) is embedded in the edge branch.  ...  [36] proposed a hierarchical image co-saliency detection framework as a coarse-to-fine strategy for capturing this pattern. Jin et al.  ... 
doi:10.1109/access.2021.3138782 fatcat:infeutdfoffsdg6gqi3oz63p4a

A Review of Co-saliency Detection Technique: Fundamentals, Applications, and Challenges [article]

Dingwen Zhang, Huazhu Fu, Junwei Han, Ali Borji, Xuelong Li
2017 arXiv   pre-print
co-saliency, and designing effective computational frameworks to formulate co-saliency.  ...  As a novel branch of visual saliency, co-saliency detection refers to the discovery of common and salient foregrounds from two or more relevant images, and can be widely used in many computer vision tasks  ...  For example, Fu et al. has provided an efficient and general robust image pair-distance based on the co-saliency maps [29] .  ... 
arXiv:1604.07090v5 fatcat:j7zqwqaowndrbcuoazzizkuqr4

Deep Visual Odometry with Adaptive Memory [article]

Fei Xue and Xin Wang and Junqiu Wang and Hongbin Zha
2020 arXiv   pre-print
With the guidance of previous outputs, we adopt a spatial-temporal attention to select features for each view based on the co-visibility in feature domain.  ...  Global information is crucial for alleviating accumulated errors. However, it is challenging to effectively preserve such information for end-to-end systems.  ...  Specifically, we present a novel framework for learning monocular VO estimation in an end-to-end fashion.  ... 
arXiv:2008.01655v1 fatcat:oivwiy5oyrgntkry46awtwyvlq

Discovering Primary Objects in Videos by Saliency Fusion and Iterative Appearance Estimation

Jiong Yang, Gangqiang Zhao, Junsong Yuan, Xiaohui Shen, Zhe Lin, Brian Price, Jonathan Brandt
2016 IEEE transactions on circuits and systems for video technology (Print)  
In this paper, we propose a new method for detecting primary objects in unconstrained videos in a completely automatic setting.  ...  In order to obtain high quality saliency estimations from both appearance and motion cues, we propose a novel self-adaptive saliency map fusion method by learning the reliability of saliency maps from  ...  [26] proposed to discover co-salient objects from a group of images by fusing the intra-image saliency map and the inter-image saliency map.  ... 
doi:10.1109/tcsvt.2015.2433171 fatcat:j36vuagvujauhoeplcttngwo64

UC-Net: Uncertainty Inspired RGB-D Saliency Detection via Conditional Variational Autoencoders [article]

Jing Zhang, Deng-Ping Fan, Yuchao Dai, Saeed Anwar, Fatemeh Sadat Saleh, Tong Zhang, Nick Barnes
2020 arXiv   pre-print
saliency maps for each input image by sampling in the latent space.  ...  In this paper, we propose the first framework (UCNet) to employ uncertainty for RGB-D saliency detection by learning from the data labeling process.  ...  Through this iterative hiding strategy, we obtain multiple saliency maps for each input RGB-D image pair, which reflects the diversity/uncertainty from human labeling.  ... 
arXiv:2004.05763v1 fatcat:bk5q4rbn45hgrlyin2pbdwfc2u
« Previous Showing results 1 — 15 out of 123 results