编程代写 MULTIMEDIA RETRIEVAL

MULTIMEDIA RETRIEVAL
Course Review
Course Review
 Course Survey

Copyright By PowCoder代写 加微信 powcoder

 Feedback on Project Presentation  Course Summary
 Exam Preparation
School of Computer Science

Course Survey
 Please complete the course survey to provide us your feedback
 https://student-surveys.sydney.edu.au/
School of Computer Science
Course Content
 Multimedia Basics
 Multimedia Retrieval
Retrieval basics
 Data representation
 Similarity measurement
Advanced topics
School of Computer Science

Multimedia Basics
 Digitization concept  Sampling
 Quantization  Aliasing
 Digital image acquisition and Representation
 Digital video acquisition and representation
 Digital audio acquisition and representation  Waveform, frequency & spectrum
The content marked with (*) are for understanding only.
School of Computer Science
Retrieval Basics
 Information retrieval
 Motivations, challenges, and general paradigm
 Document preprocessing
 parsing/tokenization  Stemming
 Stopwordremoval
 Indexing and index
 Similarity Measurement
 Relevance feedback
 Query Expansion, Summarization, and visualization
 Evaluation
 Web Search
 Characteristics of Web
 Paradigm of web search systems
 Crawling
 PageRank:motivationandalgorithm  HITS:motivationandalgorithm
School of Computer Science

Multimedia Retrieval Basics
 Content-basedretrieval
 Motivations and challenges  Issues
 Audioretrieval/classification  Features, applications
 Image retrieval
 Feature extraction
 Color: color space, techniques (color histogram, color moments, color coherence vector) and their properties
 Texture: categorization, techniques and their properties (no calculating)
 Shape: categorization, techniques and their properties (no calculating)
 Spatial: 2D, 2D-G, 2D-C (*)
 Others features: Compressed domain, graph (*)
 Issues of feature extraction  Case studies
School of Computer Science
Multimedia Retrieval Basics
 Other issues of CBR
 Feature combination  Issues
 Normalization: intra- & inter-
 Similarity measure: distance functions and properties
 Relevance feedback: concepts and techniques
 Indexing: concepts, indexing techniques and their properties, issues
 Performance evaluation  Metrics
 Benchmark
School of Computer Science

Multimedia Retrieval Basics
 Video retrieval
 Access video content: fundamental aspects  Analysis, representation, browsing, retrieval
 Segmentation
 Shot detection
 Key-frame extraction
 Object segmentation
 Scene/event detection
 Story segmentation
 Video abstract/skimming
 Representation
 Key-frame based
 Shot-based: motion based, object based, …
 Applications
 Video retrieval: by motion/trajectories
 Video annotation: events in soccer video, dialogue detection, news video analysis  Video classification: movie genre classification, finding commercials in video
School of Computer Science
Social Media
 Social multimedia
 Attributes/properties  Applications
 User profile
 User context
 User interaction
School of Computer Science

Large Scale Retrieval
 Semantic Gap
 Image/Video Annotation/Tagging Co-occurrence approach Translation approach Classification approach
 Bag-of-Visual-Words model
School of Computer Science
Sketch based Image Retrieval (SBIR)
 Motivation of SBIR
 Conventional Methods Edge representation Large scale SBIR
 Deep Learning based Methods Categorical SBIR Fine-grained SBIR
School of Computer Science

Recommender Systems
 Background
 Recommendation algorithms  Collaborative filtering
 User based
 Model based
 Matrix factorization
 Content-based
 Product, document, image, video, audio
 Learning based
 Context Aware Recommendation  Evaluation
School of Computer Science
Summarization
 Text summarization  TextRank/LexRank
 Video summarization
Various categories of approaches
 Strength and limitations  Applications
School of Computer Science

Exam Preparation
 Materials
 Lecture notes
 Master core concepts and techniques
 Reference books, such as
 Book1:Chapter1,2,3,5,6,7,8,12,14,20  Book2:Chapter1,2,4,6,7,8,19,20,21
 Tutorials
 Expectations
 To understand
 Concepts, contents, and principles
 To be skilful
 Practice algorithms/techniques with calculating
 Solving problems  Analyzing results  Summarize ideas
School of Computer Science
Sample (Sub)Questions
 Explain whether the indexing method employed in textual information retrieval can be similarly utilized for multimedia information retrieval. [6 marks]
 Consider a collection made of the following 4 documents d1, d2, d3, and d4 (one document per line in italic):
d1: John gives a book to Mary
d2: John who reads a book loves Mary
d3: Who does John think Mary loves
d4: John thinks a book is a good gift
Perform a reasonable pre-processing (i.e. stop word removal and stemming) and build an index for these documents to support keyword based queries. [8 marks]
 Explain one issue with collaborative filtering. [3 marks]
 Consider the performance of following email anti-spam system against the ground truth. [3 marks]
We have a sample of 15 emails. The system reports that the following emails as spam: {1,4,7,8,11,13}, while the ground truth (labelled by human) denotes email {1,3,7,8,9,11,13,15} as spam. Calculate precision, recall and f-measure of the system
 Suppose now you have an album of photos on your mobile taken from different trips, including photos of yourself and other people, photos of food dishes, as well as scenic photos without people. Design a fully automatic system using what you have learned in this unit, to organize the photo album by putting related photos together. [8 marks]
Note that Metadata and Geo-data will not be available in this case; your system should only consider the visual information in the photos.
School of Computer Science

Final Exam
 2-hour + 10 min reading
 Short-answer questions
No multiple choice questions
Problem solving
Each question may have multiple sub-questions
 Writing/Drawing/Typing and submission
School of Computer Science
Final Exam
 Open book (scenario 2): locally saved notes on the student’s computer and paper-based resources (including printed/handwritten notes and textbooks).
 Exam Guide
 https://canvas.sydney.edu.au/courses/27821/pages/sem-1-2022-process-
for-final-exams#step7
 Resources on the Taking online exams
 https://canvas.sydney.edu.au/courses/23380
1. NOonlineresources (including UoS Canvas resources and website search such as Google)
2. DoNOTusebrowser to open PDF files.
School of Computer Science

Capstone Projects on Multimedia Computing (12cpt/18cpt/Honours)
 MultimediaInformationRetrieval
 Video/Text/Multi-modal Summarization
 Sketch Retrieval, Video Moment Retrieval, Cross-Modal/Multi-modal Retrieval, Conversational Retrieval
 HumanMotionAnalysis,Modeling,Animation,andSynthesis
 Human action recognition, 3D human/cloth animation, 3D human reconstruction  Human emotion and affect analysis
 ContentGeneration
 Video prediction and generation (e.g., talking head), view synthesis, sketch/line-art
colorization, audio/speech generation, 3D scene reconstruction
 HealthandMedicine
 Surgical Video Analysis, Medical Image Analysis, EEG signal analysis
 Agricultureandearthobservation  Remote sensing image analysis
School of Computer Science
Wish You All Great Success!
 Secrets of Success
 http://www.ted.com/talks/richard_st_john_s_8_se
crets_of_success.html
 Amazing Career Advice For College Grads From LinkedIn’s Billionaire
 https://www.businessinsider.com.au/amazing- career-advice-for-college-grads-from-linkedins- billionaire-founder-2013-5
School of Computer Science

程序代写 CS代考 加微信: powcoder QQ: 1823890830 Email: powcoder@163.com