A
Akihiro Sugimoto
Researcher at National Institute of Informatics
Publications - 178
Citations - 2259
Akihiro Sugimoto is an academic researcher from National Institute of Informatics. The author has contributed to research in topics: Image registration & Image segmentation. The author has an hindex of 24, co-authored 174 publications receiving 1870 citations. Previous affiliations of Akihiro Sugimoto include Kyoto University & Bosch.
Papers
More filters
Proceedings ArticleDOI
Fast unsupervised ego-action learning for first-person sports videos
TL;DR: This work addresses the novel task of discovering first-person action categories (which it is called ego-actions) which can be useful for such tasks as video indexing and retrieval and investigates the use of motion-based histograms and unsupervised learning algorithms to quickly cluster video content.
Journal ArticleDOI
Anabranch network for camouflaged object segmentation
TL;DR: This paper proposes a general end-to-end network, called the Anabranch Network, that leverages both classification and segmentation tasks and possesses the second branch for classification to predict the probability of containing camouflaged object(s) in an image.
Proceedings ArticleDOI
Using individuality to track individuals: Clustering individual trajectories in crowds using local appearance and frequency trait
TL;DR: The key novelty of the method is to make use of a person's individuality, that is, the gait features and the temporal consistency of local appearance to track each individual in a crowd.
Journal ArticleDOI
Video Salient Object Detection Using Spatiotemporal Deep Features
Trung-Nghia Le,Akihiro Sugimoto +1 more
TL;DR: The proposed method first segments an input video into multiple scales and then computes a saliency map at each scale level using STD features with STCRF, a new spatiotemporal conditional random field to compute saliency from STD features.
Proceedings ArticleDOI
Saliency-based image editing for guiding visual attention
TL;DR: A method for editing an image, when given a region in the image, to synthesize the image in which the region is most salient, and results confirm that the image editing method naturally draws the human visual attention toward the authors' specified region.