1 / 19

Video Summarization via Transferrable Structured Learning

Video Summarization via Transferrable Structured Learning. Presenter: PENG, Peng 2011-3-29. Outline. Paper present Transfer learning in Social Network. Video Summarization. What is Video Summarization?. Video Summarization. Video Summarization. Assumption in this paper:

maren
Download Presentation

Video Summarization via Transferrable Structured Learning

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript

  1. Video Summarization via Transferrable Structured Learning Presenter: PENG, Peng 2011-3-29

  2. Outline • Paper present • Transfer learning in Social Network

  3. Video Summarization • What is Video Summarization?

  4. Video Summarization

  5. Video Summarization • Assumption in this paper: • Each shot is accompanied by certain textual information • Textual information and video information are highly correlated (e.g., TV series)

  6. Video Summarization

  7. Video Summarization

  8. Video Summarization

  9. Video Summarization

  10. Video Summarization

  11. Video Summarization

  12. Video Summarization

  13. Video Summarization • Problem: • How to select some representative shots beforehand? • How to know the ground truth?

  14. Transfer Learning • Ds(X, P(X)), Ts(Y, P(Y|X)) • Dt(X, P(X)), Tt(Y, P(Y|X)) • In social network, what can be the same and what can be different?

  15. Q&A

  16. Thank You!

  17. Transfer Learning in Social Networks • Large amounts of unlabeled data • How to avoid negative transfer?

  18. Topics in Social Networks • Community Detection and Graph-based Clustering • Information Influence, Diffusion and Outbreak Detection • Link Prediction and Collaborative Filtering • Social Tagging and Learning • Collective intelligence and Crowd-sourcing

  19. Transfer Learning • What is the sufficient and necessary condition for positive transfer? • How to keep consistency between the source data and the target data? • How to guarantee the correctness of the transferred data in the target tasks? • What is the way to measure the relatedness between two different tasks?

More Related