Corpus ID: 593434

EXMOVES: Classifier-based Features for Scalable Action Recognition

@article{Tran2014EXMOVESCF,
  title={EXMOVES: Classifier-based Features for Scalable Action Recognition},
  author={Du Tran and L. Torresani},
  journal={CoRR},
  year={2014},
  volume={abs/1312.5785}
}

Du Tran, L. Torresani

Published 2014

Computer Science

CoRR

This paper introduces EXMOVES, learned exemplar-based features for efficient recognition of actions in videos. The entries in our descriptor are produced by evaluating a set of movement classifiers over spatial-temporal volumes of the input sequence. Each movement classifier is a simple exemplar-SVM trained on low-level features, i.e., an SVM learned using a single annotated positive space-time volume and a large number of unannotated videos. Our representation offers two main advantages… CONTINUE READING

View PDF on arXiv

Save to Library

Create Alert

Cite

Launch Research Feed