搜索资源列表
-
1下载：
本文提出了多个基于半监督学习的自动视频标注方法。通过对几种常见的半监督学习方法，如自训练、互训练以及Co一EM等方法的分析，针对它们(主要是自训练和互训练方法)在视频标注应用中的局限，在提高分类的准确性和模型更新等方面做了深入研究，提出了相应的改进措施。
-This paper presents a number of semi-supervised learning-based automatic video annotation methods. Through several comm
-
-
0下载：
进行半监督转倒式训练
通过半监督学习进行分类-for semi-supervised maching learning,the paper is 《Large Scale Transductive SVMs》
-
-
0下载：
CVPR2012_oral
Weakly Supervised Structured Output Learning for Semantic Segmentation-We address the problem of weakly supervised semantic
segmentation. The training images are labeled only by the
classes they contain, not by their location in t
-
-
0下载：
用来图像检索的，SSMetric半监督学习距离图像检索Used for image retrieval, SSMetric a semi-supervised learning distance image retrieval
-Used for image retrieval, SSMetric a semi-supervised learning distance image retrieval
-
-
1下载：
semi-supervised learning 半监督局部线性嵌入-semi-supervised learning
-
-
0下载：
基于图的半监督学习算法，matlab代码-Semi-supervised learning algorithm based on graph, matlab code. . . .
-
-
0下载：
A Comparative Evaluation of Deep Belief Nets in Semi-supervised Learning
-
-
0下载：
在机器学习领域，支持向量机SVM(Support Vector Machine）是一个有监督的学习模型，通常用来进行模式识别、分类、以及回归分析-In the field of machine learning, support vector machine SVM (Support Vector Machine) is a supervised learning model, typically used for pattern recognition, classification, and
-
-
0下载：
对图像做spca有监督的主成分分析降维，并通过RBF神经网络学习得到一个模型，并投影到原图来降噪-supervised manifold learning
-
-
0下载：
人脸识别是一个有监督学习过程，首先利用训练集构造一个人脸模型，然后将测试集与训练集进行匹配，找到与之对应的训练集头像。最容易的方式是直接利用欧式距离计算测试集的每一幅图像与训练集的每一幅图像的距离，然后选择距离最近的图像作为识别的结果。(Face recognition is a supervised learning process. Firstly, a face model is constructed by training set, and then the test set is m
-
-
0下载：
We develop a new edge detection algorithm, holistically-nested edge detection (HED), which performs image-to-image prediction by means of a deep learning model that leverages fully convolutional neural networks and deeply-supervised nets. HED automat
-
-
0下载：
This paper presents a novel yet intuitive approach to unsupervised feature learning. Inspired by the human visual(effective visual representation Specifically we use unsupervised motion-based segmentation on videos to obtain segments)
-
-
1下载：
半监督学习(Semi-Supervised Learning，SSL)是模式识别和机器学习领域研究的重点问题，是监督学习与无监督学习相结合的一种学习方法。半监督学习使用大量的未标记数据，以及同时使用标记数据，来进行模式识别工作。当使用半监督学习时，将会要求尽量少的人员来从事工作，同时，又能够带来比较高的准确性
-
