• DOI:10.1109/ICCV.2015.518
Corpus ID: 280441

Selecting Relevant Web Trained Concepts for Automated Event Retrieval

@article{Singh2015SelectingRW,
  title={Selecting Relevant Web Trained Concepts for Automated Event Retrieval},
  author={B. Singh and Xintong Han and Zhe Wu and V. Morariu and L. Davis},
  journal={2015 IEEE International Conference on Computer Vision (ICCV)},
  year={2015},
  pages={4561-4569}
}

B. Singh, Xintong Han, +2 authors L. Davis

Published 2015

Computer Science

2015 IEEE International Conference on Computer Vision (ICCV)

Complex event retrieval is a challenging research problem, especially when no training videos are available. An alternative to collecting training videos is to train a large semantic concept bank a priori. Given a text description of an event, event retrieval is performed by selecting concepts linguistically related to the event description and fusing the concept responses on unseen videos. However, defining an exhaustive concept lexicon and pre-training it requires vast computational resources… CONTINUE READING

View on IEEE

arxiv.org

Save to Library

Create Alert

Cite

Launch Research Feed