Efficient Object Localization and Segmentation in Weakly Labeled Videos

@inproceedings{Rochan2014EfficientOL,
  title={Efficient Object Localization and Segmentation in Weakly Labeled Videos},
  author={Mrigank Rochan and Yang Wang},
  booktitle={ISVC},
  year={2014}
}
In this paper, we tackle the problem of efficiently segmenting objects in weakly labeled videos. Internet videos (e.g., YouTube) are often associated with a semantic tag describing the main object within the video. However, this tag does not provide any spatial or temporal information about the object within the video. So these videos are weakly labeled. We propose a novel and efficient approach to localize the object of interest within the video and perform pixel-level segmentation. Given a… CONTINUE READING

Figures, Tables, and Topics from this paper.

Citations

Publications citing this paper.
SHOWING 1-9 OF 9 CITATIONS

An unsupervised video foreground co-localization and segmentation process by incorporating motion cues and frame features

  • International Conference on Graphic and Image Processing
  • 2018
VIEW 4 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Unsupervised Learning of Foreground Object Segmentation

  • International Journal of Computer Vision
  • 2019
VIEW 2 EXCERPTS
CITES BACKGROUND

Unsupervised Learning from Video to Detect Foreground Objects in Single Images

  • 2017 IEEE International Conference on Computer Vision (ICCV)
  • 2017
VIEW 1 EXCERPT
CITES METHODS

Efficient transductive semantic segmentation

  • 2016 IEEE Winter Conference on Applications of Computer Vision (WACV)
  • 2016
VIEW 1 EXCERPT
CITES BACKGROUND

Latent SVM for Object Localization in Weakly Labeled Videos

  • 2015 12th Conference on Computer and Robot Vision
  • 2015

References

Publications referenced by this paper.
SHOWING 1-10 OF 18 REFERENCES

Efficient Image and Video Co-localization with Frank-Wolfe Algorithm

Armand Joulin, Kevin Tang, Li Fei-Fei
  • ECCV
  • 2014
VIEW 6 EXCERPTS
HIGHLY INFLUENTIAL

Segmenting Objects in Weakly Labeled Videos

  • 2014 Canadian Conference on Computer and Robot Vision
  • 2014
VIEW 10 EXCERPTS

Discriminative Segment Annotation in Weakly Labeled Video

Kevin Tang, Rahul Sukthankar, Jay Yagnik, Li Fei-Fei
  • 2013 IEEE Conference on Computer Vision and Pattern Recognition
  • 2013
VIEW 1 EXCERPT

Geometric Context from Videos

  • 2013 IEEE Conference on Computer Vision and Pattern Recognition
  • 2013