Social negative bootstrapping for visual categorization
Proceedings of the 1st ACM International Conference on Multimedia Retrieval
Instant Bag-of-Words served on a laptop
Proceedings of the 1st ACM International Conference on Multimedia Retrieval
Classroom video assessment and retrieval via multiple instance learning
AIED'11 Proceedings of the 15th international conference on Artificial intelligence in education
Text and image subject classifiers: dense works better
MM '11 Proceedings of the 19th ACM international conference on Multimedia
Exploitation of time constraints for (sub-)event recognition
J-MRE '11 Proceedings of the 2011 joint ACM workshop on Modeling and representing events
Fusing concept detection and geo context for visual search
Proceedings of the 2nd ACM International Conference on Multimedia Retrieval
SUPER: towards real-time event recognition in internet videos
Proceedings of the 2nd ACM International Conference on Multimedia Retrieval
Categorization of a collection of pictures into structured events
Proceedings of the 2nd ACM International Conference on Multimedia Retrieval
Robust image retrieval using bag of visual words with fuzzy codebooks and fuzzy assignment
Proceedings of the 12th International Conference on Knowledge Management and Knowledge Technologies
Proceedings of the 20th ACM international conference on Multimedia
Proceedings of the 20th ACM international conference on Multimedia
Enhanced representation and multi-task learning for image annotation
Computer Vision and Image Understanding
Exploiting language models to recognize unseen actions
Proceedings of the 3rd ACM conference on International conference on multimedia retrieval
ACM Transactions on Interactive Intelligent Systems (TiiS)
Selective Search for Object Recognition
International Journal of Computer Vision
Continuous human action recognition in real time
Multimedia Tools and Applications
| Hi-index | 0.00 |
As datasets grow increasingly large in content-based image and video retrieval, computational efficiency of concept classification is important. This paper reviews techniques to accelerate concept classification, where we show the trade-off between computational efficiency and accuracy. As a basis, we use the Bag-of-Words algorithm that in the 2008 benchmarks of TRECVID and PASCAL lead to the best performance scores. We divide the evaluation in three steps: 1) Descriptor Extraction, where we evaluate SIFT, SURF, DAISY, and Semantic Textons. 2) Visual Word Assignment, where we compare a k-means visual vocabulary with a Random Forest and evaluate subsampling, dimension reduction with PCA, and division strategies of the Spatial Pyramid. 3) Classification, where we evaluate the χ2, RBF, and Fast Histogram Intersection kernel for the SVM. Apart from the evaluation, we accelerate the calculation of densely sampled SIFT and SURF, accelerate nearest neighbor assignment, and improve accuracy of the Histogram Intersection kernel. We conclude by discussing whether further acceleration of the Bag-of-Words pipeline is possible. Our results lead to a 7-fold speed increase without accuracy loss, and a 70-fold speed increase with 3% accuracy loss. The latter system does classification in real-time, which opens up new applications for automatic concept classification. For example, this system permits five standard desktop PCs to automatically tag for 20 classes all images that are currently uploaded to Flickr.