LSMDC 2016

The challenge was presented at the "Joint 2nd Workshop on Storytelling with Images and Videos (VisStory) and Large Scale Movie Description and Understanding Challenge (LSMDC 2016)" in conjunction with ECCV 2016, Amsterdam, The Netherlands.

Thank you for participating!

The challenge slides are available here.

Challenge winners

Movie Description

1st place: Video Description by Combining Strong Representation and a Simple Nearest Neighbor Approach. Gil Levi, Dotan Kaufman, Lior Wolf (Tel Aviv University), Tal Hassner (University of Southern California) [slides]

Movie Annotation and Retrieval

1st place: Video Captioning and Retrieval Models with Semantic Attention. YoungJae Yu, Hyungjin Ko, Jongwook Choi, Gunhee Kim (Seoul National University) [slides]

2st place: Video Description by Combining Strong Representation and a Simple Nearest Neighbor Approach. Gil Levi, Dotan Kaufman, Lior Wolf (Tel Aviv University), Tal Hassner (University of Southern California)

Movie Fill-in-the-Blank

1st place: Video Captioning and Retrieval Models with Semantic Attention. YoungJae Yu, Hyungjin Ko, Jongwook Choi, Gunhee Kim (Seoul National University)

2st place: Video Fill in the Blank with Merging LSTMs. Amir Mazaheri, Dong Zhang, Mubarak Shah (University of Central Florida)

Important Dates

Challenge submission deadline: September 25th September 23th, 2016

Challenge winners notification: October 2nd September 30th, 2016

Workshop: October 16th, 2016

Tasks

This year we will have three challenge tracks:

• movie description,
• movie annotation and retrieval,
• movie fill-in-the-blank.

Prizes

We are happy no announce, that the cash prizes of 500$ for the challenge winners and 150$ for 2nd place runners are sponsored by Disney Research.

Download

Data for all three tasks can be downloaded here.

Contact

lsmdc2015+16 at gmail.com