Abstract: Pedestrian crossing intention prediction is crucial for autonomous vehicles due to their inherent inertia, yet challenging. The prevailing practice is to leverage multi-modal data that ...
Abstract: In the open world, various label sets and domain configurations give rise to a variety of Domain Adaptation (DA) setups, including closed-set, partial-set, open-set, and universal DA, as ...
With its powerful visual-language alignment capability, CLIP performs well in zero-shot and few-shot learning tasks. However, CLIP's logits suffer from serious inter-class confusion problems in ...
It is more or less normal to be confused about oneself, in various ways, at various times, under a range of circumstances. Self-confusion is a part of development, because as we change and grow, we ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results