Publication View

c ○ World Scientific Publishing Company RECENT ADVANCES IN CONTENT-BASED VIDEO ANALYSIS (2008)

Abstract

In this paper, we present major issues in video parsing, abstraction, retrieval and semantic analysis. We discuss the success, the difficulties and the expectations in these areas. In addition, we identify important opened problems that can lead to more sophisticated ways of video content analysis. For video parsing, we discuss topics in video partitioning, motion characterization and object segmentation. The success in video parsing, in general, will have a great impact on video representation and retrieval. We present three levels of abstracting video content by scene, keyframe and key object representations. These representation schemes in overall serve as a good start for video retrieval. We then describe visual features, in particular motion, and similarity measures adopted for retrieval. Next, we discuss the recent computational approaches in bridging the semantic gap for video content understanding.

Publication details

Download	http://citeseerx.ist.psu.edu/viewdoc/summary?doi=?doi=10.1.1.108.3273
Source	http://vireo.cs.cityu.edu.hk/papers/ijig01.pdf
Contributors	CiteSeerX
Repository	CiteSeerX - Scientific Literature Digital Library and Search Engine (United States)
Type	text
Language	English
Relation	10.1.1.132.5942, 10.1.1.40.5046, 10.1.1.17.7265, 10.1.1.100.7131, 10.1.1.77.8810, 10.1.1.20.7763, 10.1.1.86.4551, 10.1.1.87.9460, 10.1.1.40.242, 10.1.1.85.7902, 10.1.1.36.6101, 10.1.1.47.5499, 10.1.1.53.1601, 10.1.1.29.5850, 10.1.1.19.514, 10.1.1.43.5296, 10.1.1.19.3646, 10.1.1.115.8807, 10.1.1.48.1566, 10.1.1.56.2881, 10.1.1.15.5298, 10.1.1.110.3546, 10.1.1.30.9225, 10.1.1.21.2342, 10.1.1.108.8755, 10.1.1.37.3158, 10.1.1.17.9959, 10.1.1.103.5989, 10.1.1.43.1625, 10.1.1.44.5009, 10.1.1.5.1715, 10.1.1.38.1140, 10.1.1.83.4562, 10.1.1.63.3836, 10.1.1.78.1006, 10.1.1.39.291