In this section, we follow the recommendations in Gebru et al. For what purpose was the dataset created? Who created the dataset ( e.g., which team, research group) and on behalf of which Who funded the creation of the dataset? What do the instances that comprise the dataset represent ( e.g., documents, photos, How many instances are there in total (of each type, if appropriate)? Parts of the dataset have been created programatically.

Individual preference (IP) stability, introduced by Ahmadi et al. (ICML 2022), is a natural clustering objective inspired by stability and fairness constraints.

The cost-accuracy trade-off has been a longstanding and critical issue for deep neural networks.

To this end, we propose to treat the video frames as samples from an unknown distribution, enabling us to frame their distance calculation as an optimal transport (OT) problem. Notably, the OT - based formulation allows us to relax the previously mentioned assumptions. To further improve performance, we enhance the OT formulation by introducing two regularization terms.

In our case, we have only one object class ("insect") so the