Corpus ID: 128301287

Tripping through time: Efficient Localization of Activities in Videos

@article{Hahn2020TrippingTT,
  title={Tripping through time: Efficient Localization of Activities in Videos},
  author={Meera Hahn and Asim Kadav and James M. Rehg and H. Graf},
  journal={ArXiv},
  year={2020},
  volume={abs/1904.09936}
}

Meera Hahn, Asim Kadav, +1 author H. Graf

Published 2020

Computer Science

ArXiv

Localizing moments in untrimmed videos via language queries is a new and interesting task that requires the ability to accurately ground language into video. [...] Key Method Furthermore, TripNet uses reinforcement learning to efficiently localize relevant activity clips in long videos, by learning how to intelligently skip around the video. It extracts visual features for fewer frames to perform activity classification. In our evaluation over Charades-STA, ActivityNet Captions and the TACoS dataset, we find…Expand Abstract

View PDF on arXiv

Save to Library

Create Alert

Cite

Launch Research Feed