We aim at comparing the behavior of 5 different agents on a set of 4 videos coming from very different sources, with a crowdsourcing-based evalutation criterion.
For each video, we gave a few supervisions on a limited number of classes, which will be detailed in the pages describing the agents.
We invite users to examine the videos, and rate (some or all of) them with a score ranging from 0 up to 5 stars.
Donald duck cartoon
Pink Panther cartoon
Clip from the Get Shorty movie (HoHa2 dataset)
Webcam in our AILab@Unisi
Agent code name
Base architecture without motion constraints
Base architecture with more memory for higher layers
Base architecture which received more supervisions
Base architecture which processed a longer sequence during learning