English

Object and Text-guided Semantics for CNN-based Activity Recognition

Computer Vision and Pattern Recognition 2018-05-07 v1

Abstract

Many previous methods have demonstrated the importance of considering semantically relevant objects for carrying out video-based human activity recognition, yet none of the methods have harvested the power of large text corpora to relate the objects and the activities to be transferred into learning a unified deep convolutional neural network. We present a novel activity recognition CNN which co-learns the object recognition task in an end-to-end multitask learning scheme to improve upon the baseline activity recognition performance. We further improve upon the multitask learning approach by exploiting a text-guided semantic space to select the most relevant objects with respect to the target activities. To the best of our knowledge, we are the first to investigate this approach.

Keywords

Cite

@article{arxiv.1805.01818,
  title  = {Object and Text-guided Semantics for CNN-based Activity Recognition},
  author = {Sungmin Eum and Christopher Reale and Heesung Kwon and Claire Bonial and Clare Voss},
  journal= {arXiv preprint arXiv:1805.01818},
  year   = {2018}
}

Comments

Submitted to ICIP 2018

R2 v1 2026-06-23T01:45:22.987Z