|
|
|
题名
|
作者
|
年代
|
出处
|
被引量
|
| 1 | Region Com petition:Unify-ing Snakes,Region Growing,and Bayes/MDL for Multi-band Image Segmentation显示文摘 | SongChun Zhu Alan Yuille | 1996 | IEEE Transacti Ons On Pat-tern Analysis and Mach Ine Eintelligence1996，18，9： | 1 |
| 2 | egion competition: Unifying snakes, region growing, and Bayer/MDL for multihand image segmentation显示文摘 | Song Chun Zhu Alan Yuille | 1996 | IEEE Transactions on Pattern Analysis and Machine Intelligence1996，18，9： | 1 |
| 3 | Feature extraction from faces using deformable templates显示文摘 | Alan L. Yuille Peter W. Hallinan David S. Cohen | 1992 | International Journal of Computer Vision1992，，2： | 1 |
| 4 | Statistical edge detection:learning and evaluating edge cues显示文摘 | Konishi Scott Yuille Alan L Coughlan James M | 2003 | IEEE Transactions on Pattern Analysis and Machine Intellihence2003，25，1： | 1 |
| 5 | Region Competition: Unifying Snakes,Region Growing, and Bayes/MDL for Multibancl Image Segmentation显示文摘 | Song Chun Zhu Alan Yuille | 1996 | IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE1996，18，9： | 1 |
| 6 | Region competition: unifying snakes,region growing, and bayes/MDL for multiband image segmentation显示文摘 | Songchun Zhu Alan Yuille | 1996 | IEEE Transactions on Pattern Analysis and Machine Intelligence1996，18，9： | 1 |
| 7 | Feature extraction from faces using deformable templates显示文摘 | Alan L. Yuille Peter W. Hallinan David S. Cohen | 1992 | International Journal of Computer Vision1992，，2： | 1 |
| 8 | Region competition, unifying snakes,region growing,and Bayed/MDL for muhiband image segmentation 显示文摘 | Song Chun Zhu Alan L Yuille | 1996 | IEEE Transactions on Pattern Analysis and Machine Intelligence1996，18，9： | 1 |
| 9 | AdaBooet learning for detecting and reading text in city scenes显示文摘 | Xiangrong Chen Alan L yuille | 2004 | CVPR2004，，： | 1 |
| 10 | Statisti- cal edge detection : learning and evaluating edge cues 显示文摘 | Scott Konishi Alan L Yuille James M Coughlan | 2003 | IEEE Transactions on Pattern Analysis and Machine Intel- ligence2003，25，1： | 1 |
| 11 | Feature extraction from faces using deformable templates显示文摘 | Alan L. Yuille Peter W. Hallinan David S. Cohen | 1992 | International Journal of Computer Vision1992，，2： | 1 |
| 12 | FORMS: A flexible object recognition and modelling system显示文摘 | Song Chun Zhu Alan L. Yuille | 1996 | International Journal of Computer Vision1996，，3： | 1 |
| 13 | Featureextraction from faces using deformable templates显示文摘 | Yuille Alan L Hallinan Peter W Cohen David S | 1992 | InternationalJournal of Computer Vision1992，8，2： | 1 |
| 14 | Feature extraction from faces using deformable templates显示文摘 | Alan L. Yuille Peter W. Hallinan David S. Cohen | 1992 | International Journal of Computer Vision1992，，2： | 1 |
| 15 | Acquiring Weak Annotations for Tumor Localization in Temporal and Volumetric Data显示文摘Creating large-scale and well-annotated datasets to train AI algorithms is crucial for automated tumor detection and localization.However,with limited resources,it is challenging to determine the best type of annotations when annotating massive amounts of unlabeled data.To address this issue,we focus on polyps in colonoscopy videos and pancreatic tumors in abdominal CT scans;Both applications require significant effort and time for pixel-wise annotation due to the high dimensional nature of the data,involving either temporary or spatial dimensions.In this paper,we develop a new annotation strategy,termed Drag&Drop,which simplifies the annotation process to drag and drop.This annotation strategy is more efficient,particularly for temporal and volumetric imaging,than other types of weak annotations,such as per-pixel,bounding boxes,scribbles,ellipses and points.Furthermore,to exploit our Drag&Drop annotations,we develop a novel weakly supervised learning method based on the watershed algorithm.Experimental results show that our method achieves better detection and localization performance than alternative weak annotations and,more importantly,achieves similar performance to that trained on detailed per-pixel annotations.Interestingly,we find that,with limited resources,allocating weak annotations from a diverse patient population can foster models more robust to unseen images than allocating per-pixel annotations for a small set of images.In summary,this research proposes an efficient annotation strategy for tumor detection and localization that is less accurate than per-pixel annotations but useful for creating large-scale datasets for screening tumors in various medical modalities. | Yu-Cheng Chou Bowen Li Deng-Ping Fan Alan Yuille Zongwei Zhou | 2024 | Machine Intelligence Research2024，21，2： | 0 |
| 16 | An information theory perspective on computational vision显示文摘This paper introduces computer vision from an information theory perspective.We discuss how vision can be thought of as a decoding problem where the goal is to find the most efficient encoding of the visual scene.This requires probabilistic models which are capable of capturing the complexity and ambiguities of natural images.We start by describing classic Markov Random Field(MRF)models of images.We stress the importance of having efficient inference and learning algorithms for these models and emphasize those approaches which use concepts from information theory.Next we introduce more powerful image models that have recently been developed and which are better able to deal with the complexities of natural images.These models use stochastic grammars and hierarchical representations.They are trained using images from increasingly large databases.Finally,we described how techniques from information theory can be used to analyze vision models and measure the effectiveness of different visual cues. | Alan YUILLE | 2010 | Frontiers of Electrical and Electronic Engineering in China2010，5，3： | 0 |
| 17 | Probabilistic models of vision and max-margin methods显示文摘以概率模型在图上被定义的概率的评价在计算机视觉和相关的地提出问题是吸引人的,例如语法。图形的结构,和州的变量在他们上定义,给能描述对象和图象的复杂结构的一个富有的知识代表。在图上定义的概率分布捕获这些结构的统计可变性。这些概率模型能从与管理的有限数量训练数据被学习。但是学习这些模型受不了评估正规化常数,或分区功能的困难,能极其计算地费力的概率分布。这份报纸证明由把界限放在正规化常数上,我们能获得计算地易控制的近似。为损失功能的某些选择,令人惊讶地,我们在支持向量机器(SVM ) 使用的标准最大边缘标准获得许多,因此,我们把学习归结为标准机器学习方法。我们证明许多机器学习方法能包括多班最大边缘,顺序的回归,最大边缘 Markov 网络和分析器作为近似这样被获得到概率的方法,多重例子的学习,并且潜伏的 SVM。我们包括图象标记,对象察觉和本地化由计算机视觉应用程序说明这个工作,并且打手势评价。我们更好推测那结果能被使用更好的界限和近似获得。 | Alan YUILLE Xuming HE | 2012 | Frontiers of Electrical and Electronic Engineering in China2012，7，1： | 0 |
您所在的机构暂未开通此部分的功能，请联系管理员