Filters








223 Hits in 7.7 sec

Large Displacement Dynamic Scene Segmentation through Multiscale Saliency Flow

Yinhui ZHANG, Zifen HE
2016 IEICE transactions on information and systems  
Most unsupervised video segmentation algorithms are difficult to handle object extraction in dynamic real-world scenes with large displacements, as foreground hypothesis is often initialized with no explicit  ...  We demonstrate the effectiveness of the proposed multiscale saliency flow for segmenting dynamic real-world scenes with large displacements caused by uniform sampling of video sequences.  ...  This work was supported by the National Science Foundation of China (NSFC) under Grants 61461022 and 61302173.  ... 
doi:10.1587/transinf.2015edp7482 fatcat:psbadt7vzrfgrowzuyhekghkei

Semi-Supervised Video Salient Object Detection Using Pseudo-Labels [article]

Pengxiang Yan, Guanbin Li, Yuan Xie, Zhen Li, Chuan Wang, Tianshui Chen, Liang Lin
2019 arXiv   pre-print
Based on the same refinement network and motion information in terms of optical flow, we further propose a novel method for generating pixel-level pseudo-labels from sparsely annotated frames.  ...  Deep learning-based video salient object detection has recently achieved great success with its performance significantly outperforming any other unsupervised methods.  ...  Symbols of model categories: I+C for image-based classic unsupervised or non-deep learning methods, I+D for image-based deep learning methods, V+U for video-based unsupervised methods, V+D for video-based  ... 
arXiv:1908.04051v2 fatcat:yyedrrc2lnfq7gfz6ecfnu4usq

Video Salient Object Detection via Spatiotemporal Attention Neural Networks

Yi Tang, Wenbin Zou, Yang Hua, Zhi Jin, Xia Li
2019 Neurocomputing  
The development of unsupervised video segmentation is also similar with video saliency.  ...  The video salient object detection includes cluster-based co-saliency method (CS) [11] , space-time saliency detection (ST) [75] , segmenting saliency detection (SS) [42] , saliency-aware method (SA  ... 
doi:10.1016/j.neucom.2019.09.064 fatcat:hmmvekkitbhz7ludfmy2fc6k34

Unsupervised saliency detection based on 2D Gabor and Curvelets transforms

Sheng-hua Zhong, Yan Liu, Ling Shao, Gangshan Wu
2011 Proceedings of the Third International Conference on Internet Multimedia Computing and Service - ICIMCS '11  
In this paper, we propose a novel saliency map model called Gabor & Curvelets based Saliency Map (GCSMP) relying on 2D Gabor and Curvelet transforms.  ...  Construction of saliency map in multimedia data is useful for applications in multimedia like object segmentation, quality assessment, and object recognition.  ...  ACKNOWLEDGEMENTS This research was supported by Video Retargeting using Spatiotemporal Optimization (KFKT2011A09).  ... 
doi:10.1145/2043674.2043716 dblp:conf/icimcs/ZhongLSW11 fatcat:3pjj274jqncnbireq2idqzlieu

A Benchmark Dataset and Saliency-guided Stacked Autoencoders for Video-based Salient Object Detection [article]

Jia Li, Changqun Xia, Xiaowu Chen
2017 arXiv   pre-print
Based on this dataset, this paper proposes an unsupervised baseline approach for video-based SOD by using saliency-guided stacked autoencoders.  ...  6 image-based & deep learning, and 5 video-based & unsupervised.  ...  As shown in Fig. 8 (d) , the superpixel-based saliency can detect a large salient object as a whole (e.g., the tissue in the third row of Fig. 8 (d) ). 3) Object-based saliency.  ... 
arXiv:1611.00135v2 fatcat:qljcypesj5cqvgujyovbnvctdq

Video Saliency Detection Using Object Proposals

Fang Guo, Wenguan Wang, Jianbing Shen, Ling Shao, Jian Yang, Dacheng Tao, Y. Y. Tang
2017 IEEE Transactions on Cybernetics  
The core idea is to solve the saliency detection problem by ranking and selecting the salient proposals based on object-level saliency cues.  ...  As well as introducing this novel solution for video salient object detection, we reorganize various discriminative saliency cues and traditional saliency assumptions on object proposals.  ...  In this section, we discuss the context of the existing literature in three aspects: 1) image saliency detection; 2) video saliency detection; and 3) object proposal segmentation. A.  ... 
doi:10.1109/tcyb.2017.2761361 pmid:29990032 fatcat:x2lph2cumzdedfqjd4c4lvw7ei

A General Framework for Saliency Detection Methods [article]

Fateme Mostafaie, Zahra Nabizadeh, Nader Karimi, Shadrokh Samavi
2019 arXiv   pre-print
Saliency detection is one of the most challenging problems in the fields of image analysis and computer vision.  ...  Many approaches propose different architectures based on the psychological and biological properties of the human visual attention system.  ...  Today saliency detection has been used as a pre-processing step in many computer vision and image processing tasks such as image segmentation [5] , object recognition [6] , video/image foreground co-segmentation  ... 
arXiv:1912.12027v1 fatcat:eeejulxe3vhwtpssckdvor5ovm

Unsupervised image saliency detection with Gestalt-laws guided optimization and visual attention based refinement

Yijun Yan, Jinchang Ren, Genyun Sun, Huimin Zhao, Junwei Han, Xuelong Li, Stephen Marshall, Jin Zhan
2018 Pattern Recognition  
2018) Unsupervised image saliency detection with Gestalt-laws guided optimization and visual attention based refinement. Pattern Recognition, 79. pp. 65-78. ISSN 0031-3203 , http://dx.  ...  Integrating both mechanisms and applying to salient object detection, our results have demonstrated that the proposed method consistently outperforms a number of existing unsupervised approaches on five  ...  To this end, in this paper we focus mainly on unsupervised saliency detection.  ... 
doi:10.1016/j.patcog.2018.02.004 fatcat:duwl6dnxhzfotg7qadod4c7z3q

Discovering salient objects from videos using spatiotemporal salient region detection

Rajkumar Kannan, Gheorghita Ghinea, Sridhar Swaminathan
2015 Signal processing. Image communication  
Relatively few spatiotemporal saliency detection models have been proposed for saliency detection in videos.  ...  Recent bottom-up saliency detection approaches estimate saliency based on local, regional and global contrast [8, 9, 10] .  ...  Fig. 3 . 3 (a) Source image, (b) and (c) saliency maps est imat ed wit h superpixel based pat ch segment at ion, and uniform sampling based pat ch segment at ion, (d) ground t rut h.  ... 
doi:10.1016/j.image.2015.07.004 fatcat:tourjl47njbnfiim37tq4iuzg4

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
The goal of video saliency detection model is to locate the motion-related salient object in video sequences, which considers the motion cue and spatiotemporal constraint jointly.  ...  RGBD saliency detection, co-saliency detection, or video saliency detection.  ...  The first row presents the input images, and the second row shows the ground truth for co-saliency detection. Fig. 3 . 3 Fig. 3. Examples of the video saliency detection model on the DAVIS dataset.  ... 
arXiv:1803.03391v2 fatcat:htcmhlo32jhczehvvq6nmgzwam

Coarse-to-fine Semantic Segmentation from Image-level Labels [article]

Longlong Jing, Yucheng Chen, Yingli Tian
2018 arXiv   pre-print
In this paper, we propose a novel recursive coarse-to-fine semantic segmentation framework based on only image-level category labels.  ...  For each image, an initial coarse mask is first generated by a convolutional neural network-based unsupervised foreground segmentation model and then is enhanced by a graph model.  ...  These methods can segment moving objects in videos or generate saliency maps for images.  ... 
arXiv:1812.10885v1 fatcat:uc7dsdf6jrfkfn32abfgxcwcpe

Video Salient Object Detection Using Spatiotemporal Deep Features

Trung-Nghia Le, Akihiro Sugimoto
2018 IEEE Transactions on Image Processing  
This paper presents a method for detecting salient objects in videos where temporal information in addition to spatial information is fully taken into account.  ...  We also applied our saliency computation to the video object segmentation task, showing that our method outperforms existing video object segmentation methods.  ...  On the other hand, salient object detection (SOD) aims to detect and segment salient objects in natural scenes.  ... 
doi:10.1109/tip.2018.2849860 pmid:29985139 fatcat:slnynecivvf5jbpvmbwalmjblq

Salient Object Detection: A Survey [article]

Ali Borji, Ming-Ming Cheng, Qibin Hou, Huaizu Jiang, Jia Li
2018 arXiv   pre-print
Detecting and segmenting salient objects in natural scenes, often referred to as salient object detection, has attracted a lot of interest in computer vision.  ...  generation, and saliency for fixation prediction.  ...  prior, and color prior, to detect salient objects based on a learned feature transformation 3 .  ... 
arXiv:1411.5878v5 fatcat:aw7pqd554zdfblokxy2zgp35z4

Anchor Diffusion for Unsupervised Video Object Segmentation [article]

Zhao Yang, Qiang Wang, Luca Bertinetto, Weiming Hu, Song Bai, Philip H.S. Torr
2019 arXiv   pre-print
Unsupervised video object segmentation has often been tackled by methods based on recurrent neural networks and optical flow.  ...  We further evaluate our method on the FBMS dataset and the ViSal video saliency dataset, showing results competitive with the state of the art.  ...  We would also like to acknowledge the Royal Academy of Engineering and Five AI.  ... 
arXiv:1910.10895v1 fatcat:htt65zrbivhc5fuqeptcfloii4

Anchor Diffusion for Unsupervised Video Object Segmentation

Zhao Yang, Qiang Wang, Luca Bertinetto, Song Bai, Weiming Hu, Philip Torr
2019 2019 IEEE/CVF International Conference on Computer Vision (ICCV)  
Unsupervised video object segmentation has often been tackled by methods based on recurrent neural networks and optical flow.  ...  We further evaluate our method on the FBMS dataset and the ViSal video saliency dataset, showing results competitive with the state of the art.  ...  We would also like to acknowledge the Royal Academy of Engineering and Five AI.  ... 
doi:10.1109/iccv.2019.00102 dblp:conf/iccv/YangWBBHT19 fatcat:s7nitjbksfdsdmfedery72dybi
« Previous Showing results 1 — 15 out of 223 results