상세정보
학술대회
Incremental Learning of Novel Activity Categories from Videos
- 발행일
- 201010
- 출처
- International Conference on Virtual Systems and Multimedia (VSMM) 2010, pp.21-26
- 협약과제
- 10MC4600, 실외환경에 강인한 도로 기반 저가형 자율주행기술 개발, 유원필
- 초록
- We present a methodology for learning novel human activities incrementally. In many real-world scenarios (e.g. YouTube), new videos of novel activities are provided additively, and the system must incrementally adjust its activity models rather than retraining the entire system after each addition. We introduce our incremental codebook learning algorithm for an efficient mining of important visual words for human activities, and propose a method that incrementally trains activity models using them. The experimental results show that our approach successfully learns human activities from increasing number of training videos, while maintaining its recognition performance comparable to previous non-incremental systems. ©2010 IEEE.
- KSP 제안 키워드
- Incremental learning, Real-world, Visual words, codebook learning, human activity, learning algorithms, recognition performance