Program

8:30 – 8:45 - Opening Remarks

8:45 - 9:20 – Invited Talk – Jia Deng (Princeton)

9:20 – 9:55 – Invited Talk - Cees Snoek (University of Amsterdam & Kepler Vision Technologies)

9:55 – 11:15 – Coffee Break & Poster Session (11 papers)

11:15 – 11:50 – Invited Talk - Lorenzo Torresani (Dartmouth College & Facebook AI Research)

12:00 – 13:00 – Lunch

13:00 – 13:45 – Challenge 1 - Presentation & Winners

13:45 – 14:30 - Challenge 2 - Presentation & Winners

14:30 – 15:30 – Oral Session (4 papers)

1) Multimodal Pyramid Feature Combination for Human Action Recognition, Carlos Roig, David Varas (Vilynx Spain SLU).
2) Summarizing Long-Length Videos with GAN-Enhanced Audio/Visual Features, Hansol Lee, Gyemin Lee (Seoul National University of Science and Technology).
3) AVA-ActiveSpeaker: An Audio-Visual Dataset for Active Speaker Detection, Joseph Roth, Sourish Chaudhuri, Ondrej Klejch, Radhika Marvin‎, Andrew Gallagher, Liat Kaver, Sharadh Ramaswamy, Arkadiusz Stopczynski‎, Cordelia Schmid, Zhonghua Xi, Caroline Pantofaru (Google).
4) Learning to Detect and Retrieve Objects from Unlabeled Videos, Elad Amrani, Rami Ben-Ari, Tal Hakim, Alex Bronstein (IBM, Techion).

15:30 – 16:05 - Invited Talk - Chen Sun (Google Research)

16:05 – 16:15 – Closing Remarks