A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf
.
D2-Net: Weakly-Supervised Action Localization via Discriminative Embeddings and Denoised Activations
[article]
2021
arXiv
pre-print
This work proposes a weakly-supervised temporal action localization framework, called D2-Net, which strives to temporally localize actions using video-level supervision. Our main contribution is the introduction of a novel loss formulation, which jointly enhances the discriminability of latent embeddings and robustness of the output temporal class activations with respect to foreground-background noise caused by weak supervision. The proposed formulation comprises a discriminative and a
arXiv:2012.06440v2
fatcat:thx5tinurjh4tnuj6y4elqllp4