Fast Approximate Energy Minimization via Graph Cuts
IEEE Transactions on Pattern Analysis and Machine Intelligence
Optimization Algorithms for the Selection of Key Frame Sequences of Variable Length
ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part IV
Keyframe-based tracking for rotoscoping and animation
ACM SIGGRAPH 2004 Papers
ACM SIGGRAPH 2005 Papers
Key frame selection by motion analysis
ICASSP '96 Proceedings of the Acoustics, Speech, and Signal Processing, 1996. on Conference Proceedings., 1996 IEEE International Conference - Volume 02
Semisupervised SVM batch mode active learning with applications to image retrieval
ACM Transactions on Information Systems (TOIS)
Video SnapCut: robust video object cutout using localized classifiers
ACM SIGGRAPH 2009 papers
Dense point trajectories by GPU-accelerated large displacement optical flow
ECCV'10 Proceedings of the 11th European conference on Computer vision: Part I
Efficiently scaling up video annotation with crowdsourced marketplaces
ECCV'10 Proceedings of the 11th European conference on Computer vision: Part IV
Multiple hypothesis video segmentation from superpixel flows
ECCV'10 Proceedings of the 11th European conference on Computer vision: Part V
Hi-index | 0.00 |
Manually segmenting and labeling objects in video sequences is quite tedious, yet such annotations are valuable for learning-based approaches to object and activity recognition. While automatic label propagation can help, existing methods simply propagate annotations from arbitrarily selected frames (e.g., the first one) and so may fail to best leverage the human effort invested. We define an active frame selection problem: select k frames for manual labeling, such that automatic pixel-level label propagation can proceed with minimal expected error. We propose a solution that directly ties a joint frame selection criterion to the predicted errors of a flow-based random field propagation model. It selects the set of k frames that together minimize the total mislabeling risk over the entire sequence. We derive an efficient dynamic programming solution to optimize the criterion. Further, we show how to automatically determine how many total frames k should be labeled in order to minimize the total manual effort spent labeling and correcting propagation errors. We demonstrate our method's clear advantages over several baselines, saving hours of human effort per video.