Filters








2,624 Hits in 4.0 sec

Salient object detection for searched web images via global saliency

Peng Wang, Jingdong Wang, Gang Zeng, Jie Feng, Hongbin Zha, Shipeng Li
2012 2012 IEEE Conference on Computer Vision and Pattern Recognition  
In this paper, we deal with the problem of detecting the existence and the location of salient objects for thumbnail images on which most search engines usually perform visual analysis in order to handle  ...  Our algorithm exploits global features from multiple saliency information to directly predict the existence and the position of the salient object.  ...  Unlike the MSRA object saliency image set [16] , our database has several different aspects: Image sources. Our web images are from real searching queries.  ... 
doi:10.1109/cvpr.2012.6248054 dblp:conf/cvpr/WangWZFZL12 fatcat:e4klofoazjdy5p4nz3zhy7uvyu

Automatic Image Annotation Exploiting Textual and Visual Saliency [chapter]

Yun Gu, Haoyang Xue, Jie Yang, Zhenhong Jia
2014 Lecture Notes in Computer Science  
Then semantic communities and latent textual saliency are detected; For visual saliency, we adopt a dual-layer BoW (DL-BoW) model integrated with the local features and salient regions of the image.  ...  Automatic image annotation is an attractive service for users and administrators of online photo sharing websites.  ...  For TVSA, we use [10] to extract saliency map and detect 500D BoW feature for salient and non-salient regions respectively.  ... 
doi:10.1007/978-3-319-12643-2_12 fatcat:wpq4bcun2ffnfpymjy3jtgxywe

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
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  ...  The existing co-saliency detection algorithms mainly consist of three components: extracting effective features to represent the image regions, exploring the informative cues or factors to characterize  ...  As shown in Fig. 10 , for a given object category, we can first search for the relevant images from the Web, where many diverse views of the objects in same category are available.  ... 
arXiv:1604.07090v5 fatcat:j7zqwqaowndrbcuoazzizkuqr4

Salient object detection via local saliency estimation and global homogeneity refinement

Hsin-Ho Yeh, Keng-Hao Liu, Chu-Song Chen
2014 Pattern Recognition  
detecting salient objects in an image.  ...  Despite the idea is simple, our method can effectively achieve consistent performance for detecting object saliency.  ...  (c) The objective ground truth. Fig. 2 . 2 Examples of salient object detection. (a) shows the original images.  ... 
doi:10.1016/j.patcog.2013.11.015 fatcat:ujdn4ccf5rbsdft6rbsixel66a

Encoding based saliency detection for videos and images

Thomas Mauthner, Horst Possegger, Georg Waltner, Horst Bischof
2015 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
We evaluate our approach on several datasets, including challenging scenarios with cluttered background and camera motion, as well as salient object detection in images.  ...  We present a novel video saliency detection method to support human activity recognition and weakly supervised training of activity detection algorithms.  ...  This work was supported by the Austrian Science Foundation (FWF) under the project Advanced Learning for Tracking and Detection (I535-N23).  ... 
doi:10.1109/cvpr.2015.7298864 dblp:conf/cvpr/MauthnerPWB15 fatcat:yfvuwjah3vewzmot2ulue7t5aa

Center-surround divergence of feature statistics for salient object detection

Dominik A. Klein, Simone Frintrop
2011 2011 International Conference on Computer Vision  
In this paper, we introduce a new method to detect salient objects in images.  ...  We show that our approach outperforms eight state-of-the-art saliency detectors in terms of precision and recall.  ...  The parameters used here have shown to be reasonable for the detection of salient objects in web images.  ... 
doi:10.1109/iccv.2011.6126499 dblp:conf/iccv/KleinF11 fatcat:n2jev25rrbey5k53o4n2tkkhmy

Image saliency: From intrinsic to extrinsic context

Meng Wang, Janusz Konrad, Prakash Ishwar, Kevin Jing, Henry Rowley
2011 CVPR 2011  
We propose a novel framework for automatic saliency estimation in natural images. We consider saliency to be an anomaly with respect to a given context that can be global or local.  ...  In the case of global context, we estimate saliency in the whole image relative to a large dictionary of images.  ...  The authors would like to thank Ming Zhao and other members of the Google Video team for help with this work.  ... 
doi:10.1109/cvpr.2011.5995743 dblp:conf/cvpr/WangKIJR11 fatcat:vqjfii7znzfynayrkuokykkh5a

Weakly Supervised Learning for Salient Object Detection [article]

Huaizu Jiang
2015 arXiv   pre-print
term conditioned to the salient object existence variable, which in turn depends on both global image and regional saliency features and saliency label assignment.  ...  Moreover, many existing salient object detection models assume that at least one salient object exists in the input image.  ...  We learn two groups of model parameters for salient object detection on salient object images and background images, respectively.  ... 
arXiv:1501.07492v2 fatcat:p3efba5itzhcrleg5g27ogjk6e

Salient Object Detection: A Survey [article]

Ali Borji, Ming-Ming Cheng, Qibin Hou, Huaizu Jiang, Jia Li
2018 arXiv   pre-print
generation, and saliency for fixation prediction.  ...  Detecting and segmenting salient objects in natural scenes, often referred to as salient object detection, has attracted a lot of interest in computer vision.  ...  For global search, they train another deep neural network (DNN-G) to predict the saliency value of each salient region using a variety of global contrast features such as geometric information, global  ... 
arXiv:1411.5878v5 fatcat:aw7pqd554zdfblokxy2zgp35z4

Salient object detection: A survey

Ali Borji, Ming-Ming Cheng, Qibin Hou, Huaizu Jiang, Jia Li
2019 Computational Visual Media  
, and saliency for fixation prediction.  ...  Detecting and segmenting salient objects from natural scenes, often referred to as salient object detection, has attracted great interest in computer vision.  ...  For global search, they train another deep neural network (DNN-G) to predict the saliency value of each salient region using a variety of global contrast features such as geometric information, etc.  ... 
doi:10.1007/s41095-019-0149-9 fatcat:rwh3mzauinfj7na5ewo6wfp26e

Salient Object Subitizing

Jianming Zhang, Shugao Ma, Mehrnoosh Sameki, Stan Sclaroff, Margrit Betke, Zhe Lin, Xiaohui Shen, Brian Price, Radomir Mech
2015 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
It attains 94% accuracy in detecting the existence of salient objects, and 42-82% accuracy (chance is 20%) in predicting the number of salient objects (1, 2, 3, and 4+), without resorting to any object  ...  Finally, we demonstrate the usefulness of the proposed subitizing technique in two computer vision applications: salient object detection and object proposal.  ...  For example, SOS can help a computer vision system suppress the object detection process, until the existence of salient objects is detected, and it can also provide cues for selecting among search strategies  ... 
doi:10.1109/cvpr.2015.7299031 dblp:conf/cvpr/ZhangMSSBLSPM15 fatcat:vqzs3jw3f5dr7lrzdbi5nvzi4u

When multimedia advertising meets the new Internet era

Xian-Sheng Hua, Tao Mei, Shipeng Li
2008 2008 IEEE 10th Workshop on Multimedia Signal Processing  
The ad insertion positions are detected based on visual saliency analysis to minimize the intrusiveness to the user.  ...  have become the primary sources for online advertising.  ...  The ads are inserted into the most non-salient spatial or temporal positions within images or video streams via visual saliency analysis, as well as the ads are relevant to the visual content rather than  ... 
doi:10.1109/mmsp.2008.4665039 dblp:conf/mmsp/HuaML08 fatcat:3nsmsenbxng6nhhyir256j4igu

RGB-D Salient Object Detection Based on Discriminative Cross-modal Transfer Learning [article]

Hao Chen, Y.F. Li, Dan Su
2017 arXiv   pre-print
In this work, we propose to utilize Convolutional Neural Networks to boost the performance of depth-induced salient object detection by capturing the high-level representative features for depth modality  ...  In the proposed approach, we leverage the auxiliary data from the source modality effectively by training the RGB saliency detection network to obtain the task-specific pre-understanding layers for the  ...  Inspired by this principle, most traditional salient object detection models localize salient objects by evaluating the distinctiveness of a location with low-level visual features or searching for regions  ... 
arXiv:1703.00122v2 fatcat:ifzew4huvrgqxasxndqojw4pki

Salient Object Detection Techniques in Computer Vision—A Survey

Ashish Kumar Gupta, Ayan Seal, Mukesh Prasad, Pritee Khanna
2020 Entropy  
Relevant saliency modeling trends with key issues, core techniques, and the scope for future research work have been discussed in the context of difficulties often faced in salient object detection.  ...  A large number of salient object detection (SOD) methods have been devised to effectively mimic the capability of the human visual system to detect the salient regions in images.  ...  [152] integrated pixel-wise local estimate with the object-aware global search for robust saliency detection.  ... 
doi:10.3390/e22101174 pmid:33286942 pmcid:PMC7597345 fatcat:3p5d2nal4vhxbi2via3g7oicga

Contextual Internet Multimedia Advertising

Tao Mei, Xian-Sheng Hua
2010 Proceedings of the IEEE  
These problems are: contextual relevance that determines the selection of relevant advertisements, contextual intrusiveness which is the key to detect appropriate ad insertion positions within an image  ...  In this paper, we summarize the trend of Internet multimedia advertising and conduct a broad survey on the methodologies for advertising which are driven by the rich contents of images and videos.  ...  The ads are inserted into the non-salient spatial within images or temporal positions in video streams via visual saliency analysis.  ... 
doi:10.1109/jproc.2009.2039841 fatcat:n2yp2lmv2fdutcw32agbahwnu4
« Previous Showing results 1 — 15 out of 2,624 results