Paper Info
Title
Detecting Semantic Concepts In Consumer Videos Using Audio
Abstract
With the increasing use of audio sensors in user generated content collection, how to detect semantic concepts using audio streams has become an important research problem. In this paper, we present a semantic concept annotation system using soundtracks/audio of the video. We investigate three different acoustic feature representations for audio semantic concept annotation and explore fusion of audio annotation with visual annotation systems. We test our system on the data collection from HUAWEI Accurate and Fast Mobile Video Annotation Grand Challenge 2014. The experimental results show that our audio-only concept annotation system can detect semantic concepts significantly better than random guess. It can also provide significant complementary information to the visual-based concept annotation system for performance boost. Further detailed analysis shows that for interpreting a semantic concept both visually and acoustically, it is better to train concept models for the visual system and audio system using visual-driven and audio-driven ground truth separately.
Year
Venue
Keywords
2015
2015 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING (ICASSP)
Semantic Concept Annotation, Video Content Analysis, Audio Concept Analysis
Field
DocType
ISSN
User-generated content,Data collection,Speech coding,Annotation,Information retrieval,Visualization,Computer science,Audio mining,Feature extraction,Semantics
Conference
1520-6149
Citations 
PageRank 
References 
0
0.34
17
Authors
6
Name
Order
Citations
PageRank
Junwei Liang1449.79
Qin Jin263966.86
Xixi He382.26
Gang Yang4329.38
Jieping Xu541.77
Xirong Li6119168.62