There is No Data Like Less Data: Percepts for Video Concept Detection on Consumer-Produced Media

TitleThere is No Data Like Less Data: Percepts for Video Concept Detection on Consumer-Produced Media
Publication TypeConference Paper
Year of Publication2012
AuthorsElizalde, B. Martinez, Friedland G., Lei H., & Divakaran A.
Page(s)27-32
Other Numbers3340
Abstract

Video concept detection aims to find videos that show a certain event described as a high-level concept, e.g. “wedding ceremony" or “changing a tire". This paper presents a theoretical framework and experimental evidence suggesting that video concept detection on consumer-produced videos can be performed by what we call “percepts", which is a set of observable units with Zipfian distribution. We present an unsupervised approach to extract percepts from audio tracks, which we then use to perform experiments to provide evidence for the validity of the proposed theoretical framework using the TRECVID MED 2011 dataset. The approach suggests selecting the most relevant percepts for each concept automatically, thereby actually filtering, selecting and reducing the amount of training data needed. It is show that our framework provides a highly usable foundation for doing video retrieval on consumer- produced content and is applicable for acoustic, visual, as well as multimodal content analysis.

Acknowledgment

Supported by the Intelligence Advanced Research Projects Activity(IARPA) via Department of Interior National Business Centercontract number D11PC20066. The U.S. Government is authorizedto reproduce and distribute reprints for Governmental purposesnotwithstanding any copyright annotation thereon. The viewsand conclusion contained herein are those of the authors and shouldnot be interpreted as necessarily representing the official policies orendorsement, either expressed or implied, of IARPA, DOI/NBC, orthe U.S. Government.

URLhttps://www.icsi.berkeley.edu/pubs/speech/nodatalikelessdata12.pdf
Bibliographic Notes

Proceedings of the ACM International Workshop on Audio and Multimedia Methods for Large-Scale Video Analysis (AMVA) at ACM Multimedia 2012 (MM'12), Nara, Japan, pp. 27-32

Abbreviated Authors

B. Elizalde, G. Friedland, H. Lei, and A. Divakaran

ICSI Research Group

Audio and Multimedia

ICSI Publication Type

Article in conference proceedings