- 著者
- Yusuke HARA Xueting WANG Toshihiko YAMASAKI
- 出版者
- The Institute of Electronics, Information and Communication Engineers
- 雑誌
- IEICE TRANSACTIONS on Information and Systems (ISSN:09168532)
- 巻号頁・発行日
- vol.E104-D, no.8, pp.1349-1358, 2021-08-01
- 被引用文献数
- 1
Video inpainting is a task of filling missing regions in videos. In this task, it is important to efficiently use information from other frames and generate plausible results with sufficient temporal consistency. In this paper, we present a video inpainting method jointly using affine transformation and deformable convolutions for frame alignment. The former is responsible for frame-scale rough alignment and the latter performs pixel-level fine alignment. Our model does not depend on 3D convolutions, which limits the temporal window, or troublesome flow estimation. The proposed method achieves improved object removal results and better PSNR and SSIM values compared with previous learning-based methods.
- 著者
- Yiwei Zhang Xueting Wang Yoshiaki Sakai Toshihiko Yamasaki
- 出版者
- The Institute of Image Information and Television Engineers
- 雑誌
- ITE Transactions on Media Technology and Applications (ISSN:21867364)
- 巻号頁・発行日
- vol.9, no.4, pp.262-275, 2021 (Released:2021-10-01)
- 参考文献数
- 38
- 被引用文献数
- 1
Exploring brands that customers are likely to purchase jointly has a profound effect on marketing. This study proposes a new way to measure, or estimate the similarity between brands using social media. The proposed algorithm analyzes the daily photos and hashtags posted by each brand's followers. By clustering them and converting them into histogram-based features, we can calculate the similarity between brands. We evaluate our proposed algorithm by comparing it with the purchase logs of point/credit card companies, and answers to the questionnaires. The results show that purchase logs can predict the co-purchase behaviors in the questionnaires very well, but cannot predict customers' potential interest or willingness to buy products from new brands. On the other hand, our method can predict the users’ interest in brands with a correlation coefficient of over 0.53, which is high considering that such interest in brands is highly subjective and individual dependent.