Final Program

Time
9:00-9:10WelcomeLSCVS organizers
9:10-9:40Invited Talk - Learning to see objects by listeningAntonio Torralba (MIT)
9:40-10:10Invited Talk - Recent Progress in Spatio-Temporal Action LocationCordelia Schmid (INRIA)
10:10-10:30CV @ Scale ChallengesDario Garcia (Facebook), Manohar Paluri (Facebook), Gal Chechik (Google)
10:30-11:00Coffee break
11:00-11:30ViCom: Benchmark and Methods for Video ComprehensionDu Tran (Facebook), Maksim Bolonkin (Dartmouth), Manohar Paluri (Facebook), Lorenzo Torresani (Dartmouth)
11:30-11:45Knowledge Acquisition for Visual Question Answering via Iterative QueryingYuke Zhu (Stanford), Joseph Lim (Stanford), and Li Fei-Fei (Stanford)
11:45-12:00Tag Prediction at Flickr: a View from the Darkroom
Best paper award
Pierre Garrigues (Yahoo), Sachin Farfade (Yahoo), Hamid Izadinia (University of Washington), Kofi Boakye (Yahoo), and Yannis Kalantidis (Yahoo)
12:00-2:00Lunch
2:00-2:30Invited Talk - TorontoCity Benchmark: Towards Building Large Scale 3D Models of the WorldRaquel Urtasun (University of Toronto)
2:30-2:45What makes ImageNet good for Transfer Learning?Jacob Huh (UC Berkeley), Pulkit Agrawal (UC Berkeley), and Alexei Efros (UC Berkeley)
2:45-3:00PororoQA: Cartoon Video Series Dataset for Story UnderstandingKyungmin Kim (Seoul National University), Changjun Nan (Seoul National University), Min-Oh Heo (Seoul National University), Seong-Ho Choi (Seoul National University), and Byoung-Tak Zhang (Seoul National University)
3:00-4:00Poster Presentations & Coffee
4:00-4:30Invited Talk - Self Supervised Learning of Visual RepresentationsAbhinav Gupta (CMU)
4:30-5:00Invited Talk - Scaling-up: Image Super-resolution and Compression for the massesZehan Wang (Twitter)
5:00-5:15Closing, AwardsLSCVS organizers
Posters
3:00-4:00Knowledge Acquisition for Visual Question Answering via Iterative QueryingYuke Zhu (Stanford), Joseph Lim (Stanford), and Li Fei-Fei (Stanford)
Tag Prediction at Flickr: a View from the DarkroomPierre Garrigues (Yahoo), Sachin Farfade (Yahoo), Hamid Izadinia (University of Washington), Kofi Boakye (Yahoo), and Yannis Kalantidis (Yahoo)
What makes ImageNet good for Transfer Learning?Jacob Huh, Pulkit Agrawal and Alexei Efros
PororoQA: Cartoon Video Series Dataset for Story UnderstandingKyungmin Kim (Seoul National University), Changjun Nan (Seoul National University), Min-Oh Heo (Seoul National University), Seong-Ho Choi (Seoul National University), and Byoung-Tak Zhang (Seoul National University)
Real-Time Video Highlights for Yahoo EsportsYale Song (Yahoo Research)
Temporal Activity Detection in Untrimmed Videos with Recurrent Neural Networks

Best poster award
Alberto Montes (Universitat Politècnica de Catalunya), Amaia Salvador (Universitat Politècnica de Catalunya), Santiago Pascual (Universitat Politècnica de Catalunya), and Xavier Giro-I-Nieto (Universitat Politècnica de Catalunya)