Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data
ICML '01 Proceedings of the Eighteenth International Conference on Machine Learning
2D Conditional Random Fields for Web information extraction
ICML '05 Proceedings of the 22nd international conference on Machine learning
Exploring temporal consistency for video analysis and retrieval
MIR '06 Proceedings of the 8th ACM international workshop on Multimedia information retrieval
Evaluation campaigns and TRECVid
MIR '06 Proceedings of the 8th ACM international workshop on Multimedia information retrieval
Estimating average precision with incomplete and imperfect judgments
CIKM '06 Proceedings of the 15th ACM international conference on Information and knowledge management
A reranking approach for context-based concept fusion in video indexing and retrieval
Proceedings of the 6th ACM international conference on Image and video retrieval
Towards optimal bag-of-features for object categorization and semantic video retrieval
Proceedings of the 6th ACM international conference on Image and video retrieval
Correlative multilabel video annotation with temporal kernels
ACM Transactions on Multimedia Computing, Communications, and Applications (TOMCCAP)
Multi-cue fusion for semantic video indexing
MM '08 Proceedings of the 16th ACM international conference on Multimedia
Refining video annotation by exploiting inter-shot context
Proceedings of the international conference on Multimedia
Association and Temporal Rule Mining for Post-Filtering of Semantic Concept Detection in Video
IEEE Transactions on Multimedia
Hi-index | 0.00 |
We propose a new method to boost the performance of video annotation by exploiting concept relationship in temporal context. The motivation of our idea mainly comes from the fact that temporally continuous shots in video are generally with consistent content, so that concepts in these shots should be semantically relevant. We utilize a temporal model to describe the contributions of relevant concepts to the presence of a target concept. By connecting our model with conditional random field and adopting the learning and inference approaches of it, we could obtain the refined probability of a concept occurring in the shot, which is the leverage of temporal context and initial output of video annotation. Experimental results on the widely used TRECVID dataset exhibit the effectiveness of our method for improving video annotation accuracy.