The workshop will be held in the Computer History Museum, on the morning of October 27th with the following schedule.

9h00 — Opening
9h05Keynote by David A. Shamma and Saide Bakhshi
9h50 — Oral Session 1: Mining

  • User Group based Viewpoint Recommendation using User Attributes for Multiview Videos
  • Beyond Concept Detection: The Potential of User Intent for Image Retrieval

10h25 — Spotlights

  • ┬áImage Captioning in the Wild: How people caption images on Flickr
  • A Deep Multi-Modal Fusion Approach for Semantic Place Prediction in Social Media
  • Movie Genre Classification based on Poster Images with Deep Neural Networks
  • Robust Multi-Modal Cues for Dyadic Human Interaction Recognition

[Coffee break ~10h30]

11h00 — Oral Session 2: Modeling

  • Head Pose Recommendation for Taking Good Selfies
  • More cat than cute? Interpretable Prediction of Adjective-Noun Pairs

11h35 — Conclusion
11h40 — Poster session (all ORAL and SPOTLIGHT papers)

[Lunch ~13h00]

Comments are closed.