Embedded Files
Excited to announce MuSe2021!
MuSe Baselines +
Baselines
Baselines
See https://arxiv.org/pdf/2004.14858.pdf for detailed description. Code available on github.com.
MuSe-Wild: .2568
MuSe-Wild: .2568
MuSe-Trust: .4128
MuSe-Trust: .4128
Reporting Combined (0.5 · Arousal + 0.5 · Valence) for MuSe-Wild and Trustworthiness for MuSe-Trust , both using concordance correlation coefficient (CCC).
MuSe-Topic Target: 76.78 %
MuSe-Topic Target: 76.78 %
Reporting Combined (0.66 · F 1 + 0.34 · Unweighted Average Recall) for the topic predictions.
MuSe-Topic Emo.: 38.81 %
MuSe-Topic Emo.: 38.81 %
Reporting Combined (0.66 · F 1 + 0.34 · Unweighted Average Recall) for the 3-class valence and arousal predictions and the combined (mean) of valence and arousal.
Leaderboards
Leaderboards
We will not be making the leaderboard available until the MuSe workshop is held and the review process has passed. Please be advised that you should prepare a paper which fits the guidelines for ACM MM.
The leaderboard will be maintained after the challenge ended. In order to enter the public leaderboards, the team will need to send us:
* the test set predictions/submissions
* members of the team
* a link to a Github repository where their solution/source code is uploaded for replication of results
* a link to an ArXiv paper with 2-6 pages describing their proposed methodology, data used and results
Page updated
Google Sites
Report abuse