Filters








2,368 Hits in 5.8 sec

Non-local spatial redundancy reduction for bottom-up saliency estimation

Jinjian Wu, Fei Qi, Guangming Shi, Yongheng Lu
2012 Journal of Visual Communication and Image Representation  
In contrast to conventional methods, our approach determines the saliency by filtering out redundant contents instead of measuring their significance.  ...  To analyze the redundancy of self-repeating spatial structures, we propose a non-local self-similarity based procedure.  ...  With redundancy reduction, the proposed model successfully locates the salient parts of the image, as shown by Fig. 5(c) .  ... 
doi:10.1016/j.jvcir.2012.07.010 fatcat:qcj5wbd5ofhfzbrz4d7jx6u6va

Diversity Regularized Spatiotemporal Attention for Video-Based Person Re-identification

Shuang Li, Slawomir Bak, Peter Carr, Xiaogang Wang
2018 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition  
Features extracted from local image regions are organized by spatial attention model and are combined using temporal attention.  ...  Instead, we propose a new spatiotemporal attention model that automatically discovers a diverse set of distinctive body parts.  ...  [44] jointly train the pedestrian detection and person re-identification in a single CNN model.  ... 
doi:10.1109/cvpr.2018.00046 dblp:conf/cvpr/LiB0W18 fatcat:zkhhivnlprdt7ezuhi44uaqoga

Person Search in a Scene by Jointly Modeling People Commonness and Person Uniqueness

Yuanlu Xu, Bingpeng Ma, Rui Huang, Liang Lin
2014 Proceedings of the ACM International Conference on Multimedia - MM '14  
To bridge this gap, we propose a unified framework which jointly models the commonness of people (for detection) and the uniqueness of a person (for identification).  ...  ., people detection and person re-identification.  ...  However, in the sequential framework, the salient regions may easily be ignored by the people detector, especially if they belong to an occluded person, which results in false negatives in detection and  ... 
doi:10.1145/2647868.2654965 dblp:conf/mm/XuMHL14 fatcat:tc77dcf7x5aubb3oiwpcz6lc3i

Instance-Level Salient Object Segmentation [article]

Guanbin Li, Yuan Xie, Liang Lin, Yizhou Yu
2017 arXiv   pre-print
However, none of the existing methods is able to identify object instances in the detected salient regions.  ...  To promote further research and evaluation of salient instance segmentation, we also construct a new database of 1000 images and their pixelwise salient instance annotations.  ...  distinct object instances in detected salient regions.  ... 
arXiv:1704.03604v1 fatcat:ecfjttvyw5dwjltamvrh5j35bm

Diversity Regularized Spatiotemporal Attention for Video-based Person Re-identification [article]

Shuang Li, Slawomir Bak, Peter Carr, Xiaogang Wang
2018 arXiv   pre-print
Features extracted from local image regions are organized by spatial attention model and are combined using temporal attention.  ...  Instead, we propose a new spatiotemporal attention model that automatically discovers a diverse set of distinctive body parts.  ...  [44] jointly train the pedestrian detection and person re-identification in a single CNN model.  ... 
arXiv:1803.09882v1 fatcat:ebbaxvldbbcm7krtck4h7vrwpy

Salient Object Detection via Structured Matrix Decomposition

Houwen Peng, Bing Li, Haibin Ling, Weiming Hu, Weihua Xiong, Stephen J. Maybank
2017 IEEE Transactions on Pattern Analysis and Machine Intelligence  
We evaluate our model for salient object detection on five challenging datasets including single object, multiple objects and complex scene images, and show competitive results as compared with 24 state-of-the-art  ...  Low-rank recovery models have shown potential for salient object detection, where a matrix is decomposed into a low-rank matrix representing image background and a sparse matrix identifying salient objects  ...  ACKNOWLEDGMENTS The authors would like to thank the reviewers and editor for their helpful comments to improve the paper.  ... 
doi:10.1109/tpami.2016.2562626 pmid:28113696 fatcat:4rnbcixgxvahdi3qh7rfeibsgm

Object Recognition Using Wavelet Based Salient Points

S. Arivazhagan, R. Newlin Shebiah
2009 Open Signal Processing Journal  
Hence Patches (local features) are used to describe properties of certain region of an image.  ...  In the domain of object recognition, it is often the case that images have to be classified based on objects which make up only a very limited part of the image.  ...  The characteristics of salient points as proposed by Haralick and Shapiro [15] are are: Distinctness, Invariance, Stability, Uniqueness and Interpretability.  ... 
doi:10.2174/1876825300902010014 fatcat:rni3cnwpkvfnpl3ep4xppsth5y

Object Recognition with Wavelet-Based Salient Points [chapter]

R. Ahila Priyadharshini, S. Arivazhagan, S. Jeypriya
2012 Communications in Computer and Information Science  
Hence Patches (local features) are used to describe properties of certain region of an image.  ...  In the domain of object recognition, it is often the case that images have to be classified based on objects which make up only a very limited part of the image.  ...  The characteristics of salient points as proposed by Haralick and Shapiro [15] are are: Distinctness, Invariance, Stability, Uniqueness and Interpretability.  ... 
doi:10.1007/978-3-642-29216-3_58 fatcat:uwao67xvgjgxfk5lvfke55svhy

Real-time object segmentation based on convolutional neural network with saliency optimization for picking

2018 Journal of Systems Engineering and Electronics  
By the combination of the region proposal method based on the convolutional neural network and superpixel method, the category and location information can be used to segment objects and image redundancy  ...  The speed of object segmentation is significantly improved by the region proposal method.  ...  The loss function of this network directly corresponds to the detection performance, and the entire model is trained jointly.  ... 
doi:10.21629/jsee.2018.06.17 fatcat:e6hff35mu5arnanlhvbn7efjtu

Research on Salient Object Detection using Deep Learning and Segmentation Methods

2019 International journal of recent technology and engineering  
Detecting and segmenting salient objects in natural scenes, often referred to as salient object detection has attracted a lot of interest in computer vision and recently various heuristic computational  ...  The aim of this review work is to study about the details of methods in salient object detection.  ...  ., [9] developed the model for detection of salient objects in video sequences. Their model is composed of temporal and spatial mode.  ... 
doi:10.35940/ijrte.b1046.0982s1119 fatcat:6ofq53vb7zhx7boq4ndpraphs4

Salient Object Detection in Low Contrast Images via Global Convolution and Boundary Refinement

Nan Mu, Xin Xu, Xiaolong Zhang
2019 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)  
Benefit from the powerful features created by using deep learning technology, salient object detection has recently witnessed remarkable progresses.  ...  Our model drives the network to learn the local and global information to discriminate pixels belonging to salient objects or not, thus can produce more uniform saliency map.  ...  Introduction Salient object detection aims to locate the most distinctive objects in an image that are consistent with human visual perception.  ... 
doi:10.1109/cvprw.2019.00102 dblp:conf/cvpr/Mu0019 fatcat:yqiftioorvdjfmcifrdyvcvm6q

Salient Object Detection Techniques in Computer Vision—A Survey

Ashish Kumar Gupta, Ayan Seal, Mukesh Prasad, Pritee Khanna
2020 Entropy  
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.  ...  Detection and localization of regions of images that attract immediate human visual attention is currently an intensive area of research in computer vision.  ...  Introduction Salient object detection (SOD) is an important computer vision task aimed at precise detection and segmentation of visually distinctive image regions from the perspective of the human visual  ... 
doi:10.3390/e22101174 pmid:33286942 pmcid:PMC7597345 fatcat:3p5d2nal4vhxbi2via3g7oicga

Multi-modal Weights Sharing and Hierarchical Feature Fusion for RGBD Salient Object Detection

Fen Xiao, Bin Li, Yimu Peng, Chunhong Cao, Kai Hu, Xieping Gao
2020 IEEE Access  
Salient object detection (SOD) aims to identify and locate the most attractive regions in an image, which has been widely used in various vision tasks.  ...  Recent years, with the development of RGBD sensor technology, depth information of scenes becomes available for image understanding.  ...  While bottom-up approaches are stimuli-driven, which by aggregating low-level image features, such as color, edge and shape, to detect salient regions in a scene.  ... 
doi:10.1109/access.2020.2971509 fatcat:aze3ddzokjcy3pn764iffcibsm

Combined key-frame extraction and object-based video segmentation

Lijie Liu, Guoliang Fan
2005 IEEE transactions on circuits and systems for video technology (Print)  
On the one hand, shot-based segmentation can dramatically facilitate and enhance object-based segmentation by using key-frame extraction to select a few key-frames for statistical model training.  ...  On the other hand, object-based segmentation can be used to improve shot-based segmentation results by using model-based key-frame refinement.  ...  ACKNOWLEDGMENT The authors would like to thank the three referees whose comments and suggestions have greatly improved this paper.  ... 
doi:10.1109/tcsvt.2005.848347 fatcat:3m5t6yedfbezrivcv3baydutnu

Salient Montages from Unconstrained Videos [chapter]

Min Sun, Ali Farhadi, Ben Taskar, Steve Seitz
2014 Lecture Notes in Computer Science  
We present a novel method to generate salient montages from unconstrained videos, by finding "montageable moments" and identifying the salient people and actions to depict in each montage.  ...  Our main contributions are (1) the process of finding salient people and moments to form a montage, and (2) the application of this method to videos taken "in the wild" where the camera moves freely.  ...  We thank Microsoft, Google, Intel, the TerraSwarm research center, NSF IIS-1338054, NSF IIS-1218683, ONR N00014-13-1-0720, and ONR MURI N00014-10-1-0934 for supporting this research.  ... 
doi:10.1007/978-3-319-10584-0_31 fatcat:pi3vlctfnre7jj7ahrbofb7o2u
« Previous Showing results 1 — 15 out of 2,368 results