本文選題：社會(huì)化多媒體 + 內(nèi)容分析��； 參考：《清華大學(xué)》2013年博士論文

【摘要】：多媒體信息語(yǔ)義理解是計(jì)算機(jī)科學(xué)與技術(shù)學(xué)科的經(jīng)典問(wèn)題之一，傳統(tǒng)的多媒體內(nèi)容分析與摘要技術(shù)關(guān)注純內(nèi)容分析，數(shù)據(jù)主要來(lái)源于專(zhuān)業(yè)網(wǎng)站，質(zhì)量普遍較高；社會(huì)網(wǎng)絡(luò)的興起使得社會(huì)化多媒體內(nèi)容主要由用戶生成，具有規(guī)模大、質(zhì)量低、社會(huì)化和個(gè)性化需求高等特點(diǎn)，用戶無(wú)法高效的從海量數(shù)據(jù)中提取感興趣的信息，因此社會(huì)化多媒體的自動(dòng)語(yǔ)義分析與摘要技術(shù)愈發(fā)重要。社會(huì)化多媒體分析與摘要面臨以下挑戰(zhàn)，首先，用戶生成內(nèi)容（User Generated Content，UGC）使得多媒體信息數(shù)量激增，如何快速有效的組織和表示數(shù)據(jù)成為一大難題；其次，離散的信息發(fā)布和傳播模式使得從全局角度發(fā)現(xiàn)不同粒度的熱門(mén)話題成為自動(dòng)搜索引擎的一大障礙；最后，快餐式的信息消費(fèi)理念使得長(zhǎng)篇大論更易受忽視，，如何從海量數(shù)據(jù)中發(fā)現(xiàn)個(gè)性化的最有價(jià)值的信息是每個(gè)互聯(lián)網(wǎng)用戶正在經(jīng)歷的困境。為解決以上挑戰(zhàn)，本文分別展開(kāi)針對(duì)性的研究，研究?jī)?nèi)容主要包括： 1.提出基于以數(shù)據(jù)驅(qū)動(dòng)方式比較圖像特征的特征間優(yōu)勢(shì)互補(bǔ)的融合算法。圖像的特征表示是圖像語(yǔ)義理解的基礎(chǔ)，為解決數(shù)據(jù)組織和表示問(wèn)題，本文選取當(dāng)前最有代表性的幾種圖像特征，在大規(guī)模數(shù)據(jù)集上進(jìn)行了比較和細(xì)致分析，得到了一系列圖像特征提取的觀察數(shù)據(jù)，并在此基礎(chǔ)上以不同特征之間優(yōu)勢(shì)互補(bǔ)的思路設(shè)計(jì)了特征融合算法，實(shí)驗(yàn)表明，該融合算法可以顯著好于單一特征。 2.提出社會(huì)化多媒體數(shù)據(jù)的雙向語(yǔ)義關(guān)聯(lián)模型。社會(huì)網(wǎng)絡(luò)中的多媒體信息關(guān)聯(lián)關(guān)系是復(fù)雜多樣的，為了更好的擬合數(shù)據(jù)分布和解決熱點(diǎn)話題發(fā)現(xiàn)問(wèn)題，本文提出一種針對(duì)多模態(tài)微博數(shù)據(jù)的雙向語(yǔ)義關(guān)聯(lián)模型，該模型可以靈活的適應(yīng)數(shù)據(jù)中的多樣的多媒體多模態(tài)信息關(guān)聯(lián)，實(shí)驗(yàn)表明該模型在相關(guān)的應(yīng)用中具有良好表現(xiàn)。 3.提出社會(huì)屬性感知的視頻摘要方法。社會(huì)網(wǎng)絡(luò)中的視頻摘要相比傳統(tǒng)的電影或者體育視頻摘要具有內(nèi)容不確定性和用戶個(gè)性化需求高的新要求，本文提出一種結(jié)合內(nèi)容重要性和個(gè)性化興趣的社會(huì)屬性感知的視頻摘要方法，模型輸出為一個(gè)視頻故事板，包含用戶感興趣的個(gè)性化視頻信息，實(shí)驗(yàn)表明算法既能捕捉到視頻的重要內(nèi)容又能滿足用戶個(gè)性化興趣需求。
[Abstract]:Semantic understanding of multimedia information is one of the classic problems in computer science and technology. Traditional multimedia content analysis and abstract technology focus on pure content analysis. With the rise of social network, social multimedia content is mainly generated by users, which has the characteristics of large scale, low quality, high demand for socialization and personalization, and users can not efficiently extract information of interest from mass data. Therefore, the automatic semantic analysis and abstract technology of socialized multimedia is becoming more and more important. The challenges of socialized multimedia analysis and summary are as follows: first, user generated content (user Generated) makes the amount of multimedia information surge, and how to organize and represent data quickly and effectively becomes a big problem. The discrete mode of information distribution and dissemination makes finding hot topics of different granularity from a global perspective a big obstacle to automatic search engines. Finally, the idea of fast food consumption makes it easier to ignore the long talk. How to find the most valuable information from mass data is the dilemma that every Internet user is experiencing. In order to solve the above challenges, this paper respectively launched targeted research, the main contents of the research include: 1. This paper presents a fusion algorithm based on the complementary advantages of features compared with image features in a data-driven manner. Image feature representation is the basis of image semantic understanding. In order to solve the problem of data organization and representation, this paper selects the most representative image features and makes a comparison and detailed analysis on large-scale data sets. A series of observation data of image feature extraction are obtained, and a feature fusion algorithm is designed based on the idea of complementary advantages among different features. Experiments show that this fusion algorithm is significantly better than a single feature. 2. A bidirectional semantic association model of socialized multimedia data is proposed. The relationship between multimedia information in social networks is complex and diverse. In order to better fit the data distribution and solve the hot topic discovery problem, this paper proposes a bi-directional semantic association model for multi-modal Weibo data. The model can flexibly adapt to the multi-modal information association of multimedia in the data. Experiments show that the model has good performance in related applications. 3. A video summarization method for social attribute awareness is proposed. Compared with the traditional film or sports video summary, the video summary in social network has the new requirements of high content uncertainty and user personalized demand. This paper presents a video summarization method which combines the social attribute perception of content importance and personalized interest. The model is outputted as a video storyboard containing personalized video information of interest to users. Experiments show that the algorithm can not only capture the important content of video but also meet the needs of users' personalized interest.
【學(xué)位授予單位】：清華大學(xué)
【學(xué)位級(jí)別】：博士
【學(xué)位授予年份】：2013
【分類(lèi)號(hào)】：TP391.41

【參考文獻(xiàn)】

相關(guān)期刊論文 前1條

1 顧建剛;邱雪娜;應(yīng)宏微;宋加濤;彭鑫;汪躍;;一種基于紋理和顏色的粒子濾波目標(biāo)跟蹤方法[J];電視技術(shù);2011年03期

本文編號(hào)：1865022