English

Best Vision Technologies Submission to ActivityNet Challenge 2018-Task: Dense-Captioning Events in Videos

Computer Vision and Pattern Recognition 2018-06-26 v1

Abstract

This note describes the details of our solution to the dense-captioning events in videos task of ActivityNet Challenge 2018. Specifically, we solve this problem with a two-stage way, i.e., first temporal event proposal and then sentence generation. For temporal event proposal, we directly leverage the three-stage workflow in [13, 16]. For sentence generation, we capitalize on LSTM-based captioning framework with temporal attention mechanism (dubbed as LSTM-T). Moreover, the input visual sequence to the LSTM-based video captioning model is comprised of RGB and optical flow images. At inference, we adopt a late fusion scheme to fuse the two LSTM-based captioning models for sentence generation.

Keywords

Cite

@article{arxiv.1806.09278,
  title  = {Best Vision Technologies Submission to ActivityNet Challenge 2018-Task: Dense-Captioning Events in Videos},
  author = {Yuan Liu and Moyini Yao},
  journal= {arXiv preprint arXiv:1806.09278},
  year   = {2018}
}

Comments

Rank 2 in ActivityNet Captions Challenge 2018