Scene Retrieval for Video Summarization Based on Text-to-Image gan

Rintaro Yanagi, Ren Togo, Takahiro Ogawa, Miki Haseyama

Abstract

We present a new scene retrieval method based on text-to-image Generative Adversarial Network (GAN) and its application to query-based video summarization. Text-to-image GAN is a deep learning method that can generate images from their corresponding sentences. In this paper, we reveal a characteristic that deep learning-based visual features extracted from images generated by text-to-image GAN include semantic information sufficiently. By utilizing the generated images as queries, the proposed method achieves higher scene retrieval performance than those of the state-of-the-art methods. In addition, we introduce a novel architecture that can consider order relationship of the input sentences to our method for realizing a target video summarization. Specifically, the proposed method generates multiple images thorough text-to-image GAN from multiple sentences summarizing target videos. Their summarized video can be obtained by performing the retrieval of corresponding scenes from the target videos according to the generated images with considering the order relationship. Experimental results show the effectiveness of the proposed method in the retrieval and summarization performance.
BibTeX
@inproceedings{yanagi2019scene,
  author = {Rintaro Yanagi and Ren Togo and Takahiro Ogawa and Miki Haseyama},
  title = {{Scene Retrieval for Video Summarization Based on Text-to-Image gan}},
  booktitle = {ICIP},
  year = {2019},
  doi = {10.1109/icip.2019.8803177},
}

Loading related content...

Figure