12Video Modeling and Retrieval

Zheng-Jun Zha

Jin Yuan

Yan-Tao Zheng

Tat-Seng Chua

12.1 Introduction

Recent advancements in processor speed, high-speed network, and the availability of massive digital storages have led to an explosive amount of video data, covering a wide range of topics from broadcast news, to documentaries, meetings, movies, and other videos. There is a compelling need for automatic modeling and efficient retrieval of these data. Most commercial video search engines provide access to videos based on the textual metadata associated with videos, including filename, surrounding text, closed captions, a speech transcript, and so on. However, the problem with text-based video retrieval is that the textual metadata are frequently ...

Get Multimedia Image and Video Processing, 2nd Edition now with the O’Reilly learning platform.

O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.