Active Frame Selection for Label Propagation in Videos

@inproceedings{Vijayanarasimhan2012ActiveFS,
  title={Active Frame Selection for Label Propagation in Videos},
  author={Sudheendra Vijayanarasimhan and Kristen Grauman},
  booktitle={ECCV},
  year={2012}
}
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 anactive frame selection problem: select k frames for manual labeling, such that automatic pixel-level… CONTINUE READING
BETA

Citations

Publications citing this paper.
SHOWING 1-10 OF 78 CITATIONS, ESTIMATED 35% COVERAGE

Selective Video Object Cutout

  • IEEE Transactions on Image Processing
  • 2017
VIEW 6 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

An Approach to Streaming Video Segmentation With Sub-Optimal Low-Rank Decomposition

  • IEEE Transactions on Image Processing
  • 2016
VIEW 4 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

Active Frame, Location, and Detector Selection for Automated and Manual Video Annotation

  • 2014 IEEE Conference on Computer Vision and Pattern Recognition
  • 2014
VIEW 7 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Discriminative Feature Learning for Video Semantic Segmentation

  • 2014 International Conference on Virtual Reality and Visualization
  • 2014
VIEW 9 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Geodesic Propagation for Semantic Labeling

  • IEEE Transactions on Image Processing
  • 2014
VIEW 7 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Supervoxel-Consistent Foreground Propagation in Video

VIEW 13 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Enhancing Boundary for Video Object Segmentation

VIEW 3 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

Human machine collaboration for foreground segmentation in images and videos

VIEW 10 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Efficient frame-sequential label propagation for video object segmentation

  • Multimedia Tools and Applications
  • 2017
VIEW 4 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2012
2019

CITATION STATISTICS

  • 13 Highly Influenced Citations

  • Averaged 16 Citations per year over the last 3 years

References

Publications referenced by this paper.
SHOWING 1-10 OF 26 REFERENCES

and J

D. Tsai, M. Flagg
  • M.Rehg. Motion Coherent Tracking with M ulti-label MRF Optimization.BMVC
  • 2010
VIEW 11 EXCERPTS
HIGHLY INFLUENTIAL

Label propagation in video sequences

  • 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition
  • 2010
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

LIVEcut: Learning-based interactive video segmentation by evaluation of multiple propagated cues

  • 2009 IEEE 12th International Conference on Computer Vision
  • 2009
VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL

LabelMe video: Building a video database with human annotations

  • 2009 IEEE 12th International Conference on Computer Vision
  • 2009
VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL

Assisted Video Object Labeling By Joint Tracking of Regions and Keypoints

  • 2007 IEEE 11th International Conference on Computer Vision
  • 2007
VIEW 7 EXCERPTS
HIGHLY INFLUENTIAL

Tracking as Repeated Figure/Ground Segmentation

  • 2007 IEEE Conference on Computer Vision and Pattern Recognition
  • 2007
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Similar Papers

Loading similar papers…