Tubelets: Unsupervised Action Proposals from Spatiotemporal Super-Voxels
Sign Up to like & getrecommendations! Published in 2017 at "International Journal of Computer Vision"
DOI: 10.1007/s11263-017-1023-9
Abstract: This paper considers the problem of localizing actions in videos as sequences of bounding boxes. The objective is to generate action proposals that are likely to include the action of interest, ideally achieving high recall… read more here.
Keywords: super voxels; proposals spatiotemporal; action proposals; spatiotemporal super ... See more keywords