Track 2: Innovation Challenge
This track aims at encouraging our participants to explore the value of the generic event boundaries on the downstream applications. All the following scenarios are allowed:
For our annotated GEBD datasets (i.e. Kinetics, HMDB, ADL, UT-Ego), use 1 or multiple of them.
Do not use any of our annotations but use generic boundaries detected or annotated by yourselves on any dataset.
Combination of 1 and 2: e.g. first train a GEBD model on our annotated datasets and then apply on another dataset to obtain large-scale pseudo boundary annotations for training a new model.
Note that if you participate in both Track 1 and Track 2, duplicate submissions or submissions with significant content overlap are NOT allowed.