Statistical analysis with missing data
Statistical analysis with missing data
Shallow parsing with conditional random fields
NAACL '03 Proceedings of the 2003 Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology - Volume 1
Incomplete-data classification using logistic regression
ICML '05 Proceedings of the 22nd international conference on Machine learning
Hidden Conditional Random Fields for Gesture Recognition
CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2
Semantic Event Detection using Conditional Random Fields
CVPRW '06 Proceedings of the 2006 Conference on Computer Vision and Pattern Recognition Workshop
Impact of imputation of missing values on classification error for discrete data
Pattern Recognition
Event detection in sports video based on generative-discriminative models
EiMM '09 Proceedings of the 1st ACM international workshop on Events in multimedia
MM '09 Proceedings of the 17th ACM international conference on Multimedia
IEEE Transactions on Multimedia - Special issue on integration of context and content
Sports video mining via multichannel segmental hidden Markov models
IEEE Transactions on Multimedia
Segmentation conditional random fields (SCRFs): a new approach for protein fold recognition
RECOMB'05 Proceedings of the 9th Annual international conference on Research in Computational Molecular Biology
Fusion of audio and motion information on HMM-based highlight extraction for baseball games
IEEE Transactions on Multimedia
Semantic analysis of soccer video using dynamic Bayesian network
IEEE Transactions on Multimedia
Video Semantic Event/Concept Detection Using a Subspace-Based Multimedia Data Mining Framework
IEEE Transactions on Multimedia
An HMM-based framework for video semantic analysis
IEEE Transactions on Circuits and Systems for Video Technology
Modeling and representing events in multimedia
MM '11 Proceedings of the 19th ACM international conference on Multimedia
| Hi-index | 0.00 |
We propose a new paradigm of for sports video mining where the game flow is used to represent the semantic evolution of a field sports game. A game flow is composed of a series of variable-length drives that summarize the whole game by a few labeled events, and each drive includes a set of consecutive plays each of which is annotated by some mid-level keywords. This paradigm delivers a multi-level semantic video understanding framework that not only supports the detection of events-of-interest but also summarizes the overall semantic evolution. Specifically, we develop an Auxiliary Segmentation Conditional Random Fields (ASCRF) to explore the game flow from broadcasting sports video sequences. Not only can the proposed ASCRF support joint segmentation and recognition of drives from a set of plays annotated by multi-channel keywords, but also is capable of dealing with the problem of missing keywords by introducing an auxiliary layer by which some useful contextual information can be learned to compensate for the possible missing keywords. The experimental results on a set of American football videos demonstrates the advantages of ASCRF for finding the game flow from a set of annotated plays and its potential for other video mining applications.