Benchmark Almanac

University of Rochester

We track 3 benchmarks that University of Rochester made or helped make.

0 in use 0 with public code 0 with a leaderboard here

Benchmarks

Name Kind Released Best score Status
StoryCloze Models pick the correct ending for a four-sentence everyday story from two candidate endings. Scored by accuracy. Commonsense Apr 2016 87.4% Dropped
Audio-Visual Event Localization Models identify an event that can be both seen and heard in a video and locate when it occurs. Video understanding Mar 2018 Not in cards
Story Cloze Winter 2018 Systems select the correct story ending on the Winter 2018 test set. CodaLab reports percentage accuracy under submission identities. Commonsense Jan 2018 Not in cards