3 citations · 9 across the 6 of their papers we have counts for
7 papers
Time-series Anomaly Detection based on Difference Subspace between Signal Subspaces
Takumi Kanai, Naoya Sogi, Atsuto Maki +1
This paper proposes a new method for anomaly detection in time-series data by incorporating the concept of difference subspace into the singular spectrum analysis (SSA). The key id…
Adaptive occlusion sensitivity analysis for visually explaining video recognition networks
Tomoki Uchiyama, Naoya Sogi, Satoshi Iizuka +2
This paper proposes a method for visually explaining the decision-making process of video recognition networks with a temporal extension of occlusion sensitivity analysis, called A…
Grassmannian learning mutual subspace method for image set recognition
Lincon S. Souza, Naoya Sogi, Bernardo B. Gatto +2
This paper addresses the problem of object recognition given a set of images as input (e.g., multiple camera sources and video frames). Convolutional neural network (CNN)-based fra…
Discriminant analysis based on projection onto generalized difference subspace
Kazuhiro Fukui, Naoya Sogi, Takumi Kobayashi +2
This paper discusses a new type of discriminant analysis based on the orthogonal projection of data onto a generalized difference subspace (GDS). In our previous work, we have demo…
Resolving Marker Pose Ambiguity by Robust Rotation Averaging with Clique Constraints
Shin-Fang Ch'ng, Naoya Sogi, Pulak Purkait +2
Planar markers are useful in robotics and computer vision for mapping and localisation. Given a detected marker in an image, a frequent task is to estimate the 6DOF pose of the mar…
Constrained Mutual Convex Cone Method for Image Set Based Recognition
Naoya Sogi, Rui Zhu, Jing-Hao Xue +1
In this paper, we propose a method for image-set classification based on convex cone models. Image set classification aims to classify a set of images, which were usually obtained…
A Method Based on Convex Cone Model for Image-Set Classification with CNN Features
Naoya Sogi, Taku Nakayama, Kazuhiro Fukui
In this paper, we propose a method for image-set classification based on convex cone models, focusing on the effectiveness of convolutional neural network (CNN) features as inputs.…