The class-wise training losses often diverge as a result of the various
...
Although transformer networks are recently employed in various vision ta...
Various deepfake detectors have been proposed, but challenges still exis...
Although the recent advancement in generative models brings diverse
adva...
Image-mixing augmentations (e.g., Mixup or CutMix), which typically mix ...
In online markets, sellers can maliciously recapture others' images on
d...
Active Learning for discriminative models has largely been studied with ...
In this paper, we propose a novel structure for a cross-modal data
assoc...
In person re-identification (ReID) task, because of its shortage of trai...
We propose a new context-aware correlation filter based tracking framewo...