Search Results for author:
Found 2 papers, 1 papers with code
ADRMX: Additive Disentanglement of Domain Features with Remix Loss
To this end, most of existing studies focus on extracting domain invariant features across the available source domains in order to mitigate the effects of inter-domain distributional changes.
DECOMPL: Decompositional Learning with Attention Pooling for Group Activity Recognition from a Single Volleyball Image
To that end, we propose a novel GAR technique for volleyball videos, DECOMPL, which consists of two complementary branches.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
