Learning a Contextual Multi-Thread Model for Movie/TV Scene Segmentation

  title={Learning a Contextual Multi-Thread Model for Movie/TV Scene Segmentation},
  author={Cailiang Liu and Xiaoyang Tan and Jun Zhu and Bo Zhang},
  journal={IEEE Transactions on Multimedia},
Compared with general videos, movies and TV shows attract a significantly larger portion of people across time and contain very rich and interesting narrative patterns of shots and scenes. In this paper, we aim to recover the inherent structure of scenes and shots in such video narratives. The obtained structure could be useful for subsequent video analysis tasks such as tracking objects across cuts, action retrieval, as well as enriching user browsing and video editing interfaces. Recent… CONTINUE READING
Highly Cited
This paper has 40 citations. REVIEW CITATIONS


Publications citing this paper.
Showing 1-10 of 21 extracted citations

Temporal video segmentation: detecting the end-of-act in circus performance videos

Multimedia Tools and Applications • 2015
View 4 Excerpts
Highly Influenced

Hierarchical Boundary-Aware Neural Encoder for Video Captioning

2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) • 2017

Scene detection of news video using CNN features

2017 10th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI) • 2017
View 1 Excerpt


Publications referenced by this paper.
Showing 1-10 of 42 references

Video scene segmentation using Markov chain Monte Carlo

IEEE Transactions on Multimedia • 2006
View 4 Excerpts
Highly Influenced

Detection and representation of scenes in videos

IEEE Transactions on Multimedia • 2005
View 9 Excerpts
Highly Influenced

Shot clustering techniques for story browsing

IEEE Transactions on Multimedia • 2004
View 4 Excerpts
Highly Influenced

Constructing table-of-content for videos

Multimedia Systems • 1999
View 5 Excerpts
Highly Influenced

Similar Papers

Loading similar papers…