Multi-channel shape-flow kernel descriptors for robust video event detection and retrieval

Authors:
Pradeep Natarajan;Shuang Wu;Shiv Vitaladevuni;Xiaodan Zhuang;Unsang Park;Rohit Prasad;Premkumar Natarajan
Affiliations:
Speech, Language and Multimedia Business Unit, Raytheon BBN Technologies, Cambridge, MA;Speech, Language and Multimedia Business Unit, Raytheon BBN Technologies, Cambridge, MA;Speech, Language and Multimedia Business Unit, Raytheon BBN Technologies, Cambridge, MA;Speech, Language and Multimedia Business Unit, Raytheon BBN Technologies, Cambridge, MA;Speech, Language and Multimedia Business Unit, Raytheon BBN Technologies, Cambridge, MA;Speech, Language and Multimedia Business Unit, Raytheon BBN Technologies, Cambridge, MA;Speech, Language and Multimedia Business Unit, Raytheon BBN Technologies, Cambridge, MA
Venue:
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part II
Year:
2012

Citing 14
Cited 1

Fast training of support vector machines using sequential minimal optimization

Advances in kernel methods
Multiresolution Gray-Scale and Rotation Invariant Texture Classification with Local Binary Patterns

IEEE Transactions on Pattern Analysis and Machine Intelligence
Distinctive Image Features from Scale-Invariant Keypoints

International Journal of Computer Vision
On Space-Time Interest Points

International Journal of Computer Vision
Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories

CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2
Speeded-Up Robust Features (SURF)

Computer Vision and Image Understanding
Visual Word Ambiguity

IEEE Transactions on Pattern Analysis and Machine Intelligence
Evaluating Color Descriptors for Object and Scene Recognition

IEEE Transactions on Pattern Analysis and Machine Intelligence
Convolutional learning of spatio-temporal features

ECCV'10 Proceedings of the 11th European conference on Computer vision: Part VI
lp-Norm Multiple Kernel Learning

The Journal of Machine Learning Research
Description of interest regions with center-symmetric local binary patterns

ICVGIP'06 Proceedings of the 5th Indian conference on Computer Vision, Graphics and Image Processing
Object recognition with hierarchical kernel descriptors

CVPR '11 Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition
Learning image representations from the pixel level via hierarchical sparse coding

CVPR '11 Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition
Learning hierarchical invariant spatio-temporal features for action recognition with independent subspace analysis

CVPR '11 Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition

We are not equally negative: fine-grained labeling for multimedia event detection

Proceedings of the 21st ACM international conference on Multimedia

Quantified Score

Hi-index	0.00

Visualization

Abstract

Despite the success of spatio-temporal visual features, they are hand-designed and aggregate image or flow gradients using a pre-specified, uniform set of orientation bins. Kernel descriptors [1] generalize such orientation histograms by defining match kernels over image patches, and have shown superior performance for visual object and scene recognition. In our work, we make two contributions: first, we extend kernel descriptors to the spatio-temporal domain to model salient flow, gradient and texture patterns in video. Further, we apply our kernel descriptors to extract features from different color channels. Second, we present a fast algorithm for kernel descriptor computation of O(1) complexity for each pixel in each video patch, producing two orders of magnitude speedup over conventional kernel descriptors and other popular motion features. Our evaluation results on TRECVID MED 2011 dataset indicate that the proposed multi-channel shape-flow kernel descriptors outperform several other features including SIFT, SURF, STIP and Color SIFT.