T
Terumasa Aoki
Researcher at Tohoku University
Publications - 8
Citations - 24
Terumasa Aoki is an academic researcher from Tohoku University. The author has contributed to research in topics: Template matching & Skeletonization. The author has an hindex of 3, co-authored 8 publications receiving 18 citations.
Papers
More filters
Proceedings ArticleDOI
Violent Scenes Detection Using Mid-Level Violence Clustering
Shinichi Goto,Terumasa Aoki +1 more
TL;DR: This work proposes a novel system for Violent Scenes Detection, which is based on the combination of visual and audio features with machine learning at segment-level, and in particular, Mid-level Violence Clustering is proposed in order for mid-level concepts to be implicitly learned, without using manually tagged annotations.
Journal ArticleDOI
Motion dense sampling and component clustering for action recognition
Kazuaki Aihara,Terumasa Aoki +1 more
TL;DR: This paper proposes Motion Dense Sampling for action recognition, which detects very informative interest points from video frames by computing sampling scale for each frame based on the size of action regions.
Proceedings ArticleDOI
Automatic Image Colorization based on Feature Lines
TL;DR: This paper presents a novel automatic image colorization method based on Feature Lines, which represents the distribution of each pixel feature vector as being elongated around the lines so that it is able to assemble the similar feature pixels into one feature line.
Journal ArticleDOI
Color Segmentation Based Depth Adjustment for 3D Model Reconstruction from a Single Input Image
Vicky Sintunata,Terumasa Aoki +1 more
Proceedings ArticleDOI
Motion Dense Sampling for Video Classification
Kazuaki Aihara,Terumasa Aoki +1 more
TL;DR: The motion dense sampling (MDS) for video classification, which detects very informative interest points from video frames by computing sampling scale for each frame based on the size of foreground regions, is proposed.