香港中文大学：XML for Interoperable Digital Video Library

Department of Computer Science Engineering The Chinese University of Hong Kong LYUO102 XML for Interoperable Digital Video Library Supervised by prof LYU, Rung Tsong Michael。● Prepared by: Chan Pik Wah, Pat Ngai cheuk han. Table

Supervised by Prof. LYU, Rung Tsong Michael Department of Computer Science & Engineering The Chinese University of Hong Kong Prepared by: Chan Pik Wah, Pat Ngai Cheuk Han, Table LYU0102 XML for Interoperable Digital Video Library

●●● ●●●● ●●●●● ●●●● ●●●●● Outline ●●●● ● Introduction toⅩVP ● Review of Project ● EXtraction Techniques Face Detection e Speech Recognition Presentation XSL ●SM|L ● Transformation

Outline ⚫ Introduction to XVIP ⚫ Review of Project ⚫ Extraction Techniques ⚫ Face Detection ⚫ Speech Recognition ⚫ Presentation ⚫ XSL ⚫ SMIL ⚫ Transformation

●●● ●●●● ●●●●● ●●●● ●●●●● Motivations ●●●● · Rapid increase in the voe uso u en aces 1二 usage of multimedia Segmented Data information Digital Compression MPEG-I for video) New approach Processing MultimediaSegment DIGITAL VIDEO (Speech, Image 凵 with Derived Data Natural Language) Off-/ine Creation LIBRARY On-line Exploration Querying via Typing or Speech Mult imedia Segment with Derived Data Indexed Database BRowsing via Multimedia Abstractions and summaries P t Outfit

Motivations ⚫ Rapid increase in the usage of multimedia information ⚫ New approach: DIGITAL VIDEO LIBRARY Project Outline

●●● ●●●● ●●●●● ●●●● ●●●●● Motivations ●●●● ●●●● o Little attention paying on video information extraction and storage Scalability of the system in terms of adding new extraction components o Lack of a generic framework for presentation and visualization of video information Project Outline

Motivations ⚫ Little attention paying on video information extraction and storage ⚫ Scalability of the system in terms of adding new extraction components ⚫ Lack of a generic framework for presentation and visualization of video information Project Outline

●●● ●●●● ●●●●● ●●●● ●●●●● Overview of Xvie ●●●● ●●●● Formⅵideo By the Store as XML SMIIL developed tool Shot breat Scene Change Information DVOCR with XsL present in Face Detection Name different way Audio Speech Recognition→ Transcript y Peop上 Inft MOd Ⅵ isualization and Channel Information Information Presentation R In dexing and Project Outline

Overview of XVIP Project Outline

●●● ●●●● ●●●●● ●●●● Achievements in last semester 案①:輯但橡酰⑦說明田 Control Update View D日自?暴B州 Movie Control 厂 Extracted Information Control Control for Scene Change v Scene Chang F Position of the movie Control for VOCD Control for Playing Movie NDⅡ IMPUTE 華人民共和 南车日本三經度 三台灣 221114E中 is is the scene at Os 钕甸寮因 t-C VIDEO E-A TYPE #A YALUE 白 C FRAME cAmovue-Micromoft Vial C 感吸绕合%O国下午0157 P t Outlin

Achievements in last semester Project Outline

●●● ●●●● ●●●●● ●●●● Achievements in this semester 3: Control for Scene Change IMic On 其 Position of the movie Contrad for vOCD Cantral tor Paying Mavie Coatrol for Face Detecter ND川 稼度 国卖 is the scene at 0s FIles generate击 style Sheet 国tmn lnformation. P Cities PEople 广 Use Template 智 rescript.rt 2山的口垂口|mm △/的Q业。步上年且见 Project Outline

Achievements in this semester Project Outline

●●● ●●●● ●●●●● ●●●● ●●●●● Extraction Techniques ●●●● 圖國■國园 Scene Changes d△L Camera Motion rany statio static slate pan- zoom stave ns salle Face Detection Text Detection Word Relevance募 Audio level Extraction Techniques

Extraction Techniques Text Detection Camera Motion Face Detection Scene Changes Word Relevance Audio Level Extraction Techniques

●●● ●●●● ●●●●● ●●●● ●●●●● Face Detection ●●●● Object-presence detections are also an important technique Identify and index features to support image similarity matching. Face detection is a good example Extraction Techniques

Face Detection ⚫ Object-presence detections are also an important technique. ⚫ Identify and index features to support image similarity matching. Face detection is a good example Extraction Techniques

●●● ●●●● ●●●●● ●●●● ●●●●● Face Detection ●●●● o Name of people appearing in the video o How they are interacting with the environment o More searchable 毛目分桑之二睡米 Extraction Techniques

Face Detection ⚫ Name of people appearing in the video ⚫ How they are interacting with the environment ⚫ More searchable Extraction Techniques