论文写作之摘要

1.要求

（1）形式上

• 字数：200-350
• 语法：句式尽量简单，句子不宜太复杂，复杂容易产生歧义；

（2）内容上

背景-（现状）-（问题）-（目的）-方法-结果-（结论）

• 背景部分，第一句可以写 任务问题定义（重要性）/ 本文关注的那个点的细节的定义（现状、重要性）

2.实例分析

（1）多视图聚类 【206个词】

背景-现状-问题
% 多视图数据包含的丰富信息对各项任务的重要性
The ubiquitous information from multiple-view data, as well as the complementary information among different views, is usually beneficial for various tasks, for example, clustering, classification, denoising, and so on.
% 多视图子空间聚类的特点
Multiview subspace clustering is based on the fact that multiview data are generated from a latent subspace.
% 现有方法解决了什么问题
To recover the underlying subspace structure, a successful approach adopted recently has been sparse and/or low-rank subspace clustering.
% 现有方法不能解决的问题
Despite the fact that existing subspace clustering approaches may numerically handle multiview data, by exploring all possible pairwise correlation within views, high-order statistics that can only be captured by simultaneously utilizing all views are often overlooked.
% 目前存在的限制
As a consequence, the clustering performance of the multiview data is compromised.

目的-方法-步骤
% 方法总体描述
To address this issue, in this paper, a novel multiview clustering method is proposed by using t-product in the third-order tensor space.
% 步骤一
First, we propose a novel tensor construction method to organize multiview tensorial data, to which the tensor-tensor product can be applied.
% 步骤二
Second, based on the circular convolution operation, multiview data can be effectively represented by a t-linear combination with sparse and low-rank penalty using self-expressiveness.

实验
Our extensive experimental results on face, object, digital image, and text data demonstrate that the proposed method outperforms the state-ofthe- art methods for a range of criteria.

（2）成本有效的目标检测 【320个词】

背景
% 问题的重要性
Though quite challenging, leveraging large-scale unlabeled or partially labeled data in learning systems (e.g., model/classifier training) has attracted increasing attentions due to its fundamental importance.
% 目前已有研究
To address this problem, many active learning (AL) methods have been proposed that employ up-to-date detectors to retrieve representative minority samples according to predefined confidence or uncertainty thresholds.
% 目前存在的问题
However, these AL methods cause the detectors to ignore the remaining majority samples (i.e., those with low uncertainty or high prediction confidence).

方法
% 方法概述
In this paper, by developing a principled active sample mining (ASM) framework, we demonstrate that cost-effective mining samples from these unlabeled majority data are a key to train more powerful object detectors while minimizing user effort.
% 方法具体描述
Specifically, our ASM framework involves a switchable sample selection mechanism for determining whether an unlabeled sample should be manually annotated via AL or automatically pseudolabeled via a novel self-learning process.
% 方法特点
The proposed process can be compatible with minibatch- based training (i.e., using a batch of unlabeled or partially labeled data as a one-time input) for object detection.
% 方法具体步骤
In this process, the detector, such as a deep neural network, is first applied to the unlabeled samples (i.e., object proposals) to estimate their labels and output the corresponding prediction confidences.
Then, our ASM framework is used to select a number of samples and assign pseudolabels to them. These labels are specific to each learning batch based on the confidence levels and additional constraints introduced by the AL process and will be discarded afterward.
Then, these temporarily labeled samples are employed for network fine-tuning.
In addition, a few samples with low-confidence predictions are selected and annotated via AL.
Notably, our method is suitable for object categories that are not seen in the unlabeled data during the learning process.

实验
Extensive experiments on two public benchmarks (i.e., the PASCAL VOC 2007/2012 data sets) clearly demonstrate that our ASM framework can achieve performance comparable to that of the alternative methods but with significantly fewer annotations.

（3）具有局部结构信息的聚类 【236】

背景
% 问题定义
In pattern recognition and data mining, clustering is a classical technique to group matters of interest and has been widely employed to numerous applications.
% 目前最流行的方法
Among various clustering algorithms, K-means (KM) clustering is most popular for its simplicity and efficiency.
% 目前方法遇到的挑战概述
However, with the rapid development of the social network, high-dimensional data are frequently generated, which poses a considerable challenge to the traditional KM clustering as the curse of dimensionality.
% 目前方法的局限性分点描述
In such scenarios, it is difficult to directly cluster such highdimensional data that always contain redundant features and noises.
Although the existing approaches try to solve this problem using joint subspace learning and KM clustering, there are still the following limitations: 1) the discriminative information in low-dimensional subspace is not well captured; 2) the intrinsic geometric information is seldom considered; and 3) the optimizing procedure of a discrete cluster indicator matrix is vulnerable to noises.

方法
% 本文方法概述
In this paper, we propose a novel clustering model to cope with the above-mentioned challenges.
% 贡献一描述
Within the proposed model, discriminative information is adaptively explored by unifying local adaptive subspace learning and KM clustering.
% 贡献二描述
We extend the proposed model using a robust l2,1-norm loss function, where the robust cluster centroid can be calculated in a weighted iterative procedure.
% 贡献三描述
We also explore and discuss the relationships between the proposed algorithm and several related studies.

实验
Extensive experiments on kinds of benchmark data sets demonstrate the advantage of the proposed model compared with the state-of-the-art clustering approaches.