|
|
|
题名
|
作者
|
年代
|
出处
|
被引量
|
| 1 | Skeleton pruning as trade-off between skeleton simplicity and reconstruction error显示文摘Skeletons can be viewed as a compact shape representation in that each shape can be completely reconstructed from its skeleton.However,the usefulness of a skeletal representation is strongly limited by its instability.Skeletons suffer from contour noise in that small contour deformation may lead to large structural changes in the skeleton.A large number of skeleton computation and skeleton pruning approaches has been proposed to address this issue.Our approach differs fundamentally in the fact that we cast skeleton pruning as a trade-off between skeleton simplicity and shape reconstruction error.An ideal skeleton of a given shape should be the skeleton with a simplest possible structure that provides a best possible reconstruction of a given shape.To quantify this trade-off,we propose that the skeleton simplicity corresponds to model simplicity in the Bayesian framework,and the shape reconstruction accuracy is expressed as goodness of fit to the data.We also provide a simple algorithm to approximate the maximum of the Bayesian posterior probability which defines an order for iteratively removing the end branches to obtain the pruned skeleton.Presented experimental results obtained without any parameter tuning clearly demonstrate that the resulting skeletons are stable to boundary deformations and intra class shape variability. | SHEN Wei BAI Xiang YANG XingWei LATECKI Longin Jan | 2013 | Science China(Information Sciences)2013，56，4： | 11 |
| 2 | An open-source project for real-time image semantic segmentation显示文摘Recent years have witnessed great progress of deep convolutional neural networks(DCNNs)for solving scene understanding tasks[1-3].These vances prefer to cons true t deeper and larger network to achieve higher accuracy,yet with the sacrifice of implementing efficiency.In the context of many real-world scenarios,such as augmented reality,robo tics,and self-driving,the comp ut at ionally cheap networks are often required to carry out real-time estimation and decision.Therefore,those accura te net works requiring enormous resources are not suitable for the mobile devices(e.g.,drones,robots,and smartphones),which have limited energy overhead,restrictive memory constraints,and reduced computational capabilities.Recently,it is widely accepted that pursuing the best performance in limited computational budgets has become a primary trend in computer vision.To this end,this essay introduces an open-source project of a lightweight encoderdecoder net work(EDN)for the task of real-time image semantic segmentation. | Quan ZHOU Yu WANG Jia LIU Xin JIN Longin Jan LATECKI | 2019 | Science China(Information Sciences)2019，62，12： | 4 |
| 3 | Convexity rule for shape decomposition based on discrete contour evolution显示文摘 | Latecki Longin Jan Lakmper Rolf | 1999 | Computer Vision and Image Understanding1999，73，3： | 1 |
| 4 | Application of planarshape comparison to object retrieval in image databases显示文摘 | Latecki L J La k'mper R | 2002 | Pat- tern Recognition2002，35，1： | 1 |
| 5 | Learning context-sensitive shape similarity by graph transduction 显示文摘 | BAI X YANG X LATECKI L J | 2010 | IEEE Transactions on Pattern Analysis and Machine Intelligence2010，32，5： | 1 |
| 6 | Contour-based object detection as dominant set computation 显示文摘 | Yang X W Liu H R Latecki L J | 2012 | Pattern Recognition2012，45，5： | 1 |
| 7 | Shape similarity measure based on correspondence of visual parts 显示文摘 | Latecki L J Lak/imper R | 2000 | IEEE Transaction on Pattern Analysis and Machine Intelligence2000，22，10： | 1 |
| 8 | Shape Similarity Measure Based on Correspondence of Visual Parts显示文摘 | Latecki L J Lakamper R | 2000 | IEEE Transactions on Pattern Analysis and Machine In- telligence2000，22，10： | 1 |
| 9 | Optimal partial shape similarity显示文摘 | Longin Jan Latecki Rolf Lakaemper Diedrich Wolter | 2005 | Image and Vision Computing2005，，23： | 1 |
| 10 | A unified curvature definition for regular polygonal, and digital plannar curves 显示文摘 | Liu Hai-rong Latecki Longin J Liu Wen-yu | 2008 | International Journal of Computer Vision2008，80，1： | 1 |
| 11 | Skeleton pruning by contour partitioning with discrete curve evolution显示文摘 | Bai X Latecki L J Liu W Y | 2007 | IEEE Transactions on Pattern Analysis and Machine Intelligence2007，29，3： | 1 |
| 12 | Learning context-sensitive shape similarity by graph transduction 显示文摘 | Bai Xiang Yang Xingwei Latecki L J Liu Wenyu Tu Zhuowen | 2010 | IEEE Transactions on Pattern Analysis and Machine Intelligence2010，32，5： | 1 |
| 13 | Path similarity Skeleton graph matching显示文摘 | Bai X Latecki L J | 2008 | IEEE Transactions on Pattern Analysis and Machine Intelligence2008，30，7： | 1 |
| 14 | Path similarity skeleton graph matching显示文摘 | Xiang Bai Longin Jan Latecki Senior Member | 2008 | IEEE Transactions on Pattern Analysis and Machine Intelligence2008，30，7： | 1 |
| 15 | Learning context-sensitive shape similarity by graph transduction显示文摘 | BAI Xiang YANG Xingwei Latecki L J | 2010 | IEEE Transactions on Pattern Analysis and Machine Intelligence2010，32，5： | 1 |
| 16 | Shape similarity measure based on correspondence of visual parts显示文摘 | Latecki LJ Lakamper R | 2000 | IEEE Transactions on Pattern Analysis and Machine Intelligence2000，22，10： | 1 |
| 17 | Skeleton Pruning by Contour Partitioning with Discrete Curve Evolution显示文摘 | Bai Xiang Latecki LJ Liu Wenyu | 2007 | IEEE Transactions on Pattern Analysis and Machine Intelligence2007，29，3： | 1 |
| 18 | Learning context-sensitive shape similarity by graph transduction显示文摘 | Bai X Yang X W Latecki L J Liu W Y Tu Z W | | 0，，5： | 1 |
| 19 | Detection and recognition of contour parts based on shape similarity显示文摘 | BAI X WANG X LATECKI L J | 2008 | Pattern Recognition2008，41，7： | 1 |
| 20 | Optimal partial shape similarity显示文摘 | Latecki L J Lakaemper R Wolter D | 2005 | Image and Vision Computing2005，23，： | 1 |
您所在的机构暂未开通此部分的功能，请联系管理员