Action2vec: A crossmodal embedding approach to action learning

M Hahn, A Silva, JM Rehg - arXiv preprint arXiv:1901.00484, 2019 - arxiv.org
We describe a novel cross-modal embedding space for actions, named Action2Vec, which
combines linguistic cues from class labels with spatio-temporal features derived from video …
被引用次数：65 相关文章

Action2Vec: A Crossmodal Embedding Approach to Action Learning

M Hahn, A Silva, JM Rehg - arXiv e-prints, 2019 - ui.adsabs.harvard.edu
We describe a novel cross-modal embedding space for actions, named Action2Vec, which
combines linguistic cues from class labels with spatio-temporal features derived from video …