Makoto Okabe

Makoto Okabe

Auto-generated profile, based on publicly available information

Makoto Okabe

The University of Electro-Communications/JST CREST

Research Focus & Metrics

Academic Career Length

16Years (2011-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 February 2022 in Journal of Vision
Verified
Journal Article
Open access
PDF file
MSMasataka Sawayama
Masataka Sawayama
YDYoshinori Dobashi
Yoshinori Dobashi
MOMakoto Okabe
Makoto Okabe
KHKenchi Hosokawa
Kenchi Hosokawa
TKTakuya Koumura
Takuya Koumura
SNShin'YA Nishida
Shin'YA Nishida
Complex visual processing involved in perceiving the object materials can be better elucidated by taking a variety of research approaches. Sharing stimulus and response data is an effective strategy to make the results of different studies directly comparable and can assist researchers with different backgrounds to jump into the field. Here, we constructed a database containing several sets of material images annotated with visual discrimination performance. We created the material images using physically based computer graphics techniques and conducted psychophysical experiments with them in both laboratory and crowdsourcing settings. The observer's task was to discriminate materials on one of six dimensions (gloss contrast, gloss distinctness of image, translucent vs. opaque, metal vs. plastic, metal vs. glass, and glossy vs. painted). The illumination consistency and object geometry were also varied. We used a nonverbal procedure (an oddity task) applicable for diverse use cases, such as cross-cultural, cross-species, clinical, or developmental studies. Results showed that the material discrimination depended on the illuminations and geometries and that the ability to discriminate the spatial consistency of specular highlights in glossiness perception showed larger individual differences than in other tasks. In addition, analysis of visual features showed that the parameters of higher order color texture statistics can partially, but not completely, explain task performance. The results obtained through crowdsourcing were highly correlated with those obtained in the laboratory, suggesting that our database can be used even when the experimental conditions are not strictly controlled in the laboratory. Several projects using our dataset are underway.

1 September 2011 in Computer Graphics Forum
Verified
Journal Article
Closed access
PDF file
MOMakoto Okabe
Makoto Okabe
KAKen Anjyor
Ken Anjyor
RORikio Onai
Rikio Onai

28 December 2016 in The Visual Computer
Verified
Journal Article
Closed access
PDF file
MOMakoto Okabe
Makoto Okabe
YDYoshinori Dobashi
Yoshinori Dobashi
KAKen Anjyo
Ken Anjyo

28 November 2022 in IEEE Access
Verified
Journal Article
Open access
YWYudai Watanabe
Yudai Watanabe
MOMakoto Okabe
Makoto Okabe
YHYasunori Harada
Yasunori Harada
NKNaoji Kashima
Naoji Kashima
We propose a lightweight and accurate method for detecting anomalies in videos. Existing methods used multiple-instance learning (MIL) to determine the normal/abnormal status of each segment of the video. Recent successful researches argue that it is important to learn the temporal relationships among segments to achieve high accuracy, instead of focusing on only a single segment. Therefore we analyzed the existing methods that have been successful in recent years, and found that while it is indeed important to learn all segments together, the temporal orders among them are irrelevant to achieving high accuracy. Based on this finding, we do not use the MIL framework, but instead propose a lightweight model with a self-attention mechanism to automatically extract features that are important for determining normal/abnormal from all input segments. As a result, our neural network model has 1.3% of the number of parameters of the existing method. We evaluated the frame-level detection accuracy of our method on three benchmark datasets (UCF-Crime, ShanghaiTech, and XD-Violence) and demonstrate that our method can achieve the comparable or better accuracy than state-of-the-art methods.

29 October 2019 in IEEE Computer Graphics and Applications
Verified
Journal Article
Closed access
MOMakoto Okabe
Makoto Okabe
KNKeita Noda
Keita Noda
YDYoshinori Dobashi
Yoshinori Dobashi
KAKen Anjyo
Ken Anjyo
We propose an interactive video completion method aiming for practical use in a digital production workplace. The results of earlier automatic solutions often require a considerable amount of manual modifications to make them usable in practice. To reduce such a laborious task, our method offers an efficient editing tool. Our iterative algorithm estimates the flow fields and colors in space-time holes in the video. As in earlier approaches, our algorithm uses an L-1 data term to estimate flow fields. However, we employ a novel L-2 data term to estimate temporally coherent color transitions. Our graphics processing unit implementation enables the user to interactively complete a video by drawing holes and immediately removes objects from the video. In addition, our method successfully interpolates sparse modifications initialized by the designer. According to our subjective evaluation, the videos completed with our method look significantly better than those with other state-of-the-art approaches.