Diverse Sequential Subset Selection for Supervised Video Summarization

  title={Diverse Sequential Subset Selection for Supervised Video Summarization},
  author={Boqing Gong and Wei-Lun Chao and Kristen Grauman and Fei Sha},
Introduction Video summarization: pressing need 100 hours of new Youtube video per min 422,000 CCTV cameras in London 24/7 Sequential DPP (seqDPP) 1. Partition video into T disjoint segments 2. Introduce subset selection (of frames) variable Yt for each segment 3. Condition Yt on Yt-1 = yt-1 by DPP User study on inter-annotator agreement Data: 100 videos from Open Video Project and Youtube Annotation: 5 user summaries per video Observation: high inter-annotator agreement Generate target… CONTINUE READING
Highly Influential
This paper has highly influenced 13 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS
Highly Cited
This paper has 165 citations. REVIEW CITATIONS
113 Citations
37 References
Similar Papers


Publications citing this paper.
Showing 1-10 of 113 extracted citations

166 Citations

Citations per Year
Semantic Scholar estimates that this publication has 166 citations based on the available data.

See our FAQ for additional information.


Publications referenced by this paper.
Showing 1-10 of 37 references

Determinantal point processes for machine learning

  • Alex Kulesza, Ben Taskar
  • Foundations and Trends R © in Machine Learning,
  • 2012
Highly Influential
5 Excerpts

Similar Papers

Loading similar papers…