大規(guī)模多媒體信息管理與檢索基礎(chǔ)

內(nèi)容概要

　　大規(guī)模多媒體信息管理與檢索面臨著兩大類艱巨的技術(shù)挑戰(zhàn)。首先，這一工程問題的研究在本質(zhì)上是多領(lǐng)域、跨學(xué)科的，涉及信號(hào)處理、計(jì)算機(jī)視覺、數(shù)據(jù)庫(kù)、機(jī)器學(xué)習(xí)、神經(jīng)科學(xué)和認(rèn)知心理學(xué)；其次，一個(gè)有效的解決方案必須能解決高維數(shù)據(jù)和網(wǎng)絡(luò)規(guī)模數(shù)據(jù)的可擴(kuò)展性問題?！洞笠?guī)模多媒體信息管理與檢索基礎(chǔ)（英）：模擬人類感知數(shù)學(xué)方法》第一部分（第1～8章）著重介紹如何采用多領(lǐng)域、跨學(xué)科算法來解決特征提取及選擇、知識(shí)表示、語義分析、距離函數(shù)的制定等問題；第二部分（第9～12章）對(duì)解決高維數(shù)據(jù)和網(wǎng)絡(luò)規(guī)模數(shù)據(jù)的擴(kuò)展性問題提出了有效的處理方法。此外，《大規(guī)模多媒體信息管理與檢索基礎(chǔ)（英）：模擬人類感知數(shù)學(xué)方法》的附錄還給出了作者開發(fā)的開源軟件的下載地址。
　　《大規(guī)模多媒體信息管理與檢索基礎(chǔ)（英）：模擬人類感知數(shù)學(xué)方法》是作者在美國(guó)加州大學(xué)從事多年的教學(xué)科研及在google公司工作多年的基礎(chǔ)上編寫的?！洞笠?guī)模多媒體信息管理與檢索基礎(chǔ)（英）：模擬人類感知數(shù)學(xué)方法》適合多媒體、計(jì)算機(jī)視覺、機(jī)器學(xué)習(xí)、大規(guī)模數(shù)據(jù)處理等領(lǐng)域的研發(fā)人員閱讀，也可作為高等院校計(jì)算機(jī)專業(yè)本科生及研究生的教材或教學(xué)參考書。

作者簡(jiǎn)介

張智威，Dr. Edward Y. Chang was a professor at the Department of Electrical &Computer Engineering, University of California at Santa Barbara, before hejoined Google as a research director in 2006. Dr. Chang received his M.S.degree in Computer Science and Ph.D degree in Electrical Engineering,both from Stanford University.

書籍目錄

1 introduction - key subroutines of multimedia data
management
1.1 overview
1.2 feature extraction
1.3 similarity
1.4 learning
1.5 multimodal fusion
1.6 indexing
1.7 scalability
1.8 concluding remarks
references
2 perceptual feature extraction
2.1 introduction
2.2 dmd algorithm
2.2.1 model-based pipeline
2.2.2 data-driven pipeline
2.3 experiments
2.3.1 dataset and setup
2.3.2 model-based vs. data-driven
2.3.3 dmd vs. individual models
2.3.4 regularization tuning
2.3.5 tough categories
2.4 related reading
2.5 concluding remarks
references
3 query concept learning
3.1 introduction
3.2 support vector machines and version space
3.3 active learning and batch sampling strategies
3.3.1 theoretical foundation
3.3.2 sampling strategies
3.4 concept-dependent learning
3.4.1 concept complexity
3.4.2 limitations of active learning
3.4.3 concept-dependent active learning algorithms
3.5 experiments and discussion
3.5.1 testbed and setup
3.5.2 active vs. passive learning
3.5.3 against traditional relevance feedback schemes
3.5.4 sampling method evaluation
3.5.5 concept-dependent learning
3.5.6 concept diversity evaluation
3.5.7 evaluation summary
3.6 related reading
3.6.1 machine learning
3.6.2 relevance feedback
3.7 relation to other chapters
3.8 concluding remarks
references
4 similarity
4.1 introduction
4.2 mining image feature set
4.2.1 image testbed setup
4.2.2 feature extraction
4.2.3 feature selection
4.3 discovering the dynamic partial distance function
4.3.1 minkowski metric and its limitations
4.3.2 dynamic partial distance function
4.3.3 psychological interpretation of dynamic partial distance
function
4.4 empirical study
4.4.1 image retrieval
4.4.2 video shot-transition detection
4.4.3 near duplicated articles
4.4.4 weighted dpf vs. weighted euclidean
4.4.5 observations
4.5 related reading
4.6 concluding remarks
references
5 formulating distance functions
5.1 introduction
5.2 dfa algorithm
5.2.1 transformation model
5.2.2 distance metric learning
5.3 experimental evaluation
5.3.1 evaluation on contextual information
5.3.2 evaluation on effectiveness
5.3.3 observations
5.4 related reading
5.4.1 metric learning
5.4.2 kernel learning
5.5 concluding remarks
references
6 multimodal fusion
6.1 introduction
6.2 related reading
6.2.1 modality identification
6.2.2 modality fusion
6.3 independent modality analysis
6.3.1 pca
6.3.2 ica
6.3.3 img
6.4 super-kernel fusion
6.5 experiments
6.5.1 evaluation of modality analysis
6.5.2 evaluation of multimodal kernel fusion
6.5.3 observations
6.6 concluding remarks
references
7 fusing content and context with causality
7.1 introduction
7.2 related reading
7.2.1 photo annotation
7.2.2 probabilistic graphical models
7.3 multimodal metadata
7.3.1 contextual information
7.3.2 perceptual content
7.3.3 semantic ontology
7.4 influence diagrams
7.4.1 structure learning
7.4.2 causal strength
7.4.3 case study
7.4.4 dealing with missing attributes
7.5 experiments
7.5.1 experiment on learning structure
7.5.2 experiment on causal strength inference
7.5.3 experiment on semantic fusion
7.5.4 experiment on missing features
7.6 concluding remarks
references
8 combinational collaborative filtering， considering
personalizafion
8.1 introduction
8.2 related reading
8.3 ccf： combinational collaborative filtering
8.3.1 c-u and c-d baseline models
8.3.2 ccf model
8.3.3 gibbs & em hybrid training
8.3.4 parallelization
8.3.5 inference
8.4 experiments
8.4.1 gibbs + em vs. em
8.4.2 the orkut dataset
8.4.3 runtime speedup
8.5 concluding remarks
references
9 imbalanced data learning
9.1 introduction
9.2 related reading
9.3 kernel boundary alignment
9.3.1 conformally transforming kernel k
9.3.2 modifying kernel matrix k
9.4 experimental results
9.4.1 vector-space evaluation
9.4.2 non-vector-space evaluation
9.5 concluding remarks
references
10 psvm： parallelizing support vector machines on distributed
computers
10.1 introduction
10.2 interior point method with incomplete cholesky
factorization
10.3 psvm algorithm
10.3.1 parallel icf
10.3.2 parallel ipm
10.3.3 computing parameter b and writing back
10.4 experiments
10.4.1 class-prediction accuracy
10.4.2 scalability
10.4.3 overheads
10.5 concluding remarks
references
11 approximate high-dimensional indexing with kernel
11.1 introduction
11.2 related reading
11.3 algorithm spheredex
11.3.1 create - building the index
11.3.2 search - querying the index
11.3.3 update - insertion and deletion
11.4 experiments
11.4.1 setup
11.4.2 performance with disk ios
11.4.3 choice of parameter g
11.4.4 impact of insertions
11.4.5 sequential vs. random
11.4.6 percentage of data processed
11.4.7 summary
11.5 concluding remarks
11.5.1 range queries
11.5.2 farthest neighbor queries
references
12 speeding up latent dirichlet allocation with parallelization and
pipeline strategies
12.1 introduction
12.2 related reading
12.3 ad-lda： approximate distributed lda
12.3.1 parallel gibbs sampling and allreduce
12.3.2 mpi implementation of ad-lda
12.4 plda+
12.4.1 reduce bottleneck of ad-lda
12.4.2 framework of plda+
12.4.3 algorithm for pw processors
12.4.4 algorithm for pd processors
12.4.5 straggler handling
12.4.6 parameters and complexity
12.5 experimental results
12.5.1 datasets and experiment environment
12.5.2 perplexity
12.5.3 speedups and scalability
12.6 large-scale applications
12.6.1 mining social-network user latent behavior
12.6.2 question labeling （ql）
12.7 concluding remarks
references

章節(jié)摘錄

版權(quán)頁(yè)：插圖：Feature extraction is fundamental to all multimedia computing tasks. Features can be classified into two categories, content and context. Content refers directly to raw imagery, video, and mucic data such as pixels, motions, and tones, respectively, and their representations. Context refers to metadata collected or associated withcontent when a piece of data is acquired or published. For instance, EXIF cameraparameters and GPS location are contextual information that some digital camerascan collect. Other widely used contextual information includes surrounding texts ofan image/photo on a Web page, and social interactions on a piece of multimediadata instance. Context and content ought to be fused synergistically when analyzingmultimedia data.

編輯推薦

《大規(guī)模多媒體信息管理與檢索基礎(chǔ):模擬人類感知數(shù)學(xué)方法》：Foundations of Large-Scale Multimedia Information Management andRetrieval Mathematics of Perception covers knowledge representation andsemantic analysis of multimedia data and scalability in signal extraction,data mining, and indexing. The book is divided into two parts: Part I -Knowledge Representation and Semantic Analysis focuses on the keycomponents of mathematics of perception as it applies to data managementand retrieval. These include feature selection/reduction, knowledge repre-sentation, semantic analysis, distance function formulation for measuringsimilarity, and multimodal fusion. Part II - Scalability Issues presentsindexing and distributed methods for scaling up these components forhigh-dimensional data and Web-scale datasets. The book presents somereal-world applications and remarks on future research and developmentdirections.The book is designed for researchers, graduate students, and practitionersin the fields of Computer Vision, Machine Learning, Large-scale DataMining, Database, and Multimedia Information Retrieval.

圖書封面

評(píng)論、評(píng)分、閱讀與下載

---

    大規(guī)模多媒體信息管理與檢索基礎(chǔ) PDF格式下載

---