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.

著者

Jianbo WANG Haozhi HUANG Li SHEN Xuan 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.E106-D, no.12, pp.2085-2096, 2023-12-01

---

The image-to-image translation aims to learn a mapping between the source and target domains. For improving visual quality, the majority of previous works adopt multi-stage techniques to refine coarse results in a progressive manner. In this work, we present a novel approach for generating plausible details by only introducing a group of intermediate supervisions without cascading multiple stages. Specifically, we propose a Laplacian Pyramid Transformation Generative Adversarial Network (LapTransGAN) to simultaneously transform components in different frequencies from the source domain to the target domain within only one stage. Hierarchical perceptual and gradient penalization are utilized for learning consistent semantic structures and details at each pyramid level. The proposed model is evaluated based on various metrics, including the similarity in feature maps, reconstruction quality, segmentation accuracy, similarity in details, and qualitative appearances. Our experiments show that LapTransGAN can achieve a much better quantitative performance than both the supervised pix2pix model and the unsupervised CycleGAN model. Comprehensive ablation experiments are conducted to study the contribution of each component.

著者

Wei-Ta Chu Hideto Motomura Norimichi Tsumura 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.7, no.2, pp.60-67, 2019 (Released:2019-04-01)

参考文献数

72

被引用文献数

3

---

With the advances in digital media processing technologies and the tremendous growth in the amount of digital media that have been created, new artworks are becoming possible and drawing much attention from researchers, industry, and consumers. A related emerging research area is the evaluation of such multimedia artworks by machine learning techniques. We call this research area “attractiveness computing.” Attractiveness computing is made possible by the great accumulation of such multimedia artworks and of consumers' responses. In this paper, we review existing research on multimedia artworks analysis and attractiveness computing.