Abstract: Contrastive learning has emerged as a powerful technique in audio-visual representation learning, leveraging the natural co-occurrence of audio and visual modalities in webscale video ...
Abstract: Skeleton-based action recognition is crucial for machine intelligence. Current methods generally learn from 3D articulated motion sequences in the straightforward Euclidean space. Yet, the ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback