Context-based concept fusion with boosted conditional random fields

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

Volumn 1, Issue , 2007, Pages

  Jiang, Wei ^a   Chang, Shih Fu ^a   Loui, Alexander C ^b  

^a Dept Electrical Engineering ^*  (United States)

^b EASTMAN KODAK COMPANY   (United States)

Author keywords

Image classification; Image object detection

Indexed keywords

CONDITIONAL RANDOM FIELD (CRF); CONTEXT-BASED CONCEPT FUSION (CBCF); IMAGE OBJECT DETECTION;

IMAGE CLASSIFICATION; MATHEMATICAL MODELS; OBJECT RECOGNITION; RANDOM PROCESSES; SENSOR DATA FUSION;

CONTENT BASED RETRIEVAL;

EID: 34547507625     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2007.366066     Document Type: Conference Paper

References (10)

1. A. Amir et al. IBM research trecvid-2003 video retrieval system. Proc. NIST TRECVID Video Retrieval Evaluation Workshop, 2003.
2. J. Friedman, et al. Additive logistic regression: a statistical view of boosting. Dept. Statistics, Stanford Univ. Technical Report, 1998.
3. J. Lafferty et al. Conditional random fields: Probabilistic models for segmenting and labeling sequence data. Proc. ICML, pp.282-289, 2001.
4. K. Murphy, et al. Using the forest to see the trees: a graphical model relating features, objects, and scenes. Advances in NIPS, 2003.
5. M. Naphade et al. A factor graph framework for semantic video indexing. IEEE Trans. on CSVT, 12(1):40-52, 2002.
6. S. Paek and S.F. Chang. Experiments in constructing belief networks for image classification systems. IEEE Proc. ICIP, 3:46-49, 2000.
7. J. Smith et al. Multimedia semantic indexing using model vectors. IEEE Proc. ICME, 2:445-448, 2003.
8. rd TRECVID Workshop, Gaithersburg, USA, Nov. 2005.
9. A. Torralba et al. Contextual models for object detection using boosted random fields. Advances in NIPS, 2004.
10. TRECVID. Tree video retrieval evaluations, in http://wwwnlpir.nist. gov/projects/trecvid/.