Story Segmentation and Detection of Commercials in Broadcast News Video
ADL '98 Proceedings of the Advances in Digital Libraries Conference
On the detection and recognition of television commercials
ICMCS '97 Proceedings of the 1997 International Conference on Multimedia Computing and Systems
Matching Commercial Clips from TV Streams Using a Unique, Robust and Compact Signature
DICTA '05 Proceedings of the Digital Image Computing on Techniques and Applications
Finding and identifying unknown commercials using repeated video sequence detection
Computer Vision and Image Understanding
MULTIMEDIA '06 Proceedings of the 14th annual ACM international conference on Multimedia
Real-Time Commercial Recognition Using Color Moments and Hashing
CRV '07 Proceedings of the Fourth Canadian Conference on Computer and Robot Vision
A confidence based recognition system for TV commercial extraction
ADC '08 Proceedings of the nineteenth conference on Australasian database - Volume 75
Mining TV broadcasts for recurring video sequences
Proceedings of the ACM International Conference on Image and Video Retrieval
ARGOS: automatically extracting repeating objects from multimedia streams
IEEE Transactions on Multimedia
Simple low-dimensional features approximating NCC-based image matching
Pattern Recognition Letters
Hi-index | 0.00 |
This paper proposes a dual-stage temporal recurrence hashing algorithm for fully unsupervised and super-fast Commercial Film (CF) mining in large-scale broadcast video archives. The first-stage hashing algorithm converts a large amount of video segments into a set of temporal occurrence patterns on the basis of a luminance-based fingerprinting strategy. During the second stage, each temporal recurrence of a certain segment is mapped to an inverted index to build a recurrence hashing histogram, which is the key idea in this paper to achieve super-fast CF detection and identification. The detection and identification task is then converted into one of detecting local maximums from this hashing histogram, with one local maximum corresponding to one pair of two identical CF segments. A large-scale archive, containing a 10-hour and a 1-month sequence, was used for experimentation. Our algorithm performed CF detection and identification on the 1-month sequence in merely 87 minutes and had 90.59% detection accuracy and 98.06% localization accuracy.