social media storytelling linking
play

Social-media Storytelling Linking Hao Wu Seamus Lawless Gareth - PowerPoint PPT Presentation

Social-media Storytelling Linking Hao Wu Seamus Lawless Gareth Jones Francois Pitie The ADAPT Centre is funded under the SFI Research Centres Programme (Grant 13/RC/2106) and is co-funded under the European Regional Development Fund. Task


  1. Social-media Storytelling Linking Hao Wu Seamus Lawless Gareth Jones Francois Pitie The ADAPT Centre is funded under the SFI Research Centres Programme (Grant 13/RC/2106) and is co-funded under the European Regional Development Fund.

  2. • Task definition • Challenges & Solutions • Training • Searching • Result www.adaptcentre.ie

  3. www.adaptcentre.ie

  4. Tour France www.adaptcentre.ie

  5. www.adaptcentre.ie

  6. Challenges & Solutions www.adaptcentre.ie

  7. Video can’t be concluded by Lack of training data only one sentences. Challenges www.adaptcentre.ie

  8. Video segmentation Pre-train + Fine tuning + Length normalization Solutions www.adaptcentre.ie

  9. Data pre-processing www.adaptcentre.ie

  10. Images Videos Queries 32k 6.2k 60 Edinburgh Festival 66k 19k 58 Le Tour de France www.adaptcentre.ie

  11. Video Text Shot boundary detection Word level + Sentence level (Skip-Thought) Image sets Image Resnet-152 Visual embeddings Text representation www.adaptcentre.ie

  12. Model overview www.adaptcentre.ie

  13. www.adaptcentre.ie

  14. Training www.adaptcentre.ie

  15. Snow Pre-training Playful dogs People having meal Deep time Show Target information Museum of Edinburgh Highlights of Chris Froome Examples www.adaptcentre.ie

  16. A boy in a dark shirt is reading a book while sitting on a piano bench Pre-training Introducing Flickr30k ( High quality “image” - “text” pairs) www.adaptcentre.ie

  17. Collecting from source domain: • Identify keywords from query file. • Match keywords with data in the source. Model E.g. Keyword: taking selfies . Collecting from search engine: • Collect labels from online image search engine (Google and Bing) using story segments + event name as query. Target information collecting www.adaptcentre.ie

  18. Chris Froome pedaling Snow www.adaptcentre.ie

  19. Searching www.adaptcentre.ie

  20. Trade-off between consistency and accuracy 𝑆 𝑢 = 0.2* 𝑆 t−1 + 0.8 * 𝑁 𝑢 (M is the model raw output, R is the modified output) Search www.adaptcentre.ie

  21. There are 5 runs submitted. The main difference is the value of λ : Conf Run1 Run2 Run3 Run4 Run5 λ 3 5 12 20 50 Source Google+ Google Google Google Google Bing λ used in penalizing long videos; L denotes number of segments; Sig() is sigmoid function. Search www.adaptcentre.ie

  22. Results www.adaptcentre.ie

  23. Summary Quality 0.8 0.7 0.6 0.5 0.4 0.3 0.2 0.1 0 Run1 Run2 Run3 Run4 Run5 Edfest Tourfrance www.adaptcentre.ie

  24. Conclusion & Future Work Target specific information are crucial. Improve video representations by applying key frame selection (or building sequence model). Build a classifier to filter crawled images to make this process automatic. www.adaptcentre.ie

  25. Thanks for listening. The ADAPT Centre is funded under the SFI Research Centres Programme (Grant 13/RC/2106) and is co-funded under the European Regional Development Fund.

Download Presentation
Download Policy: The content available on the website is offered to you 'AS IS' for your personal information and use only. It cannot be commercialized, licensed, or distributed on other websites without prior consent from the author. To download a presentation, simply click this link. If you encounter any difficulties during the download process, it's possible that the publisher has removed the file from their server.

Recommend


More recommend