-
Chapter and Conference Paper
Detecting Data Drift with KS Test Using Attention Map
Data drift is a change in the distribution of data during machine learning model training and during operation. This occurs regardless of the type of data and adversely affects model performance. However, this...
-
Chapter and Conference Paper
1D Self-Attention Network for Point Cloud Semantic Segmentation Using Omnidirectional LiDAR
Understanding environment around the vehicle is essential for automated driving technology. For this purpose, an omnidirectional LiDAR is used for obtaining surrounding information and point cloud based semant...
-
Chapter and Conference Paper
Super-Class Mixup for Adjusting Training Data
Mixup is one of data augmentation methods for image recognition task, which generate data by mixing two images. Mixup randomly samples two images from training data without considering the similarity of these ...
-
Chapter and Conference Paper
Knowledge Transfer Graph for Deep Collaborative Learning
Knowledge transfer among multiple networks using their outputs or intermediate activations have evolved through manual design from a simple teacher-student approach to a bidirectional cohort one. The major com...
-
Chapter and Conference Paper
Spatial Temporal Attention Graph Convolutional Networks with Mechanics-Stream for Skeleton-Based Action Recognition
The static relationship between joints and the dynamic importance of joints leads to high accuracy in skeletal action recognition. Nevertheless, existing methods define the graph structure beforehand by skelet...
-
Chapter and Conference Paper
Coarse-to-Fine Deep Orientation Estimator for Local Image Matching
Convolutional neural networks (CNNs) have become a mainstream method for keypoint matching in addition to image recognition, object detection, and semantic segmentation. Learned Invariant Feature Transform (LI...
-
Chapter and Conference Paper
Privacy-Aware Face Recognition with Lensless Multi-pinhole Camera
Face recognition and privacy protection are closely related. A high-quality facial image is required to achieve a high accuracy in face recognition; however, this undermines the privacy of the person being pho...
-
Chapter and Conference Paper
Asymmetric Feature Representation for Object Recognition in Client Server System
This paper proposes asymmetric feature representation and efficient fitting feature spaces for object recognition in client server system. We focus on the fact that the server-side has more sufficient memory a...
-
Chapter and Conference Paper
Incremental Learning of Hand Gestures Based on Submovement Sharing
This paper presents an incremental learning method for hand gesture recognition that learns the individual movements in each gesture of a user. To recognize the movement, we use a subunit-based dynamic time wa...
-
Chapter and Conference Paper
A Subunit-Based Dynamic Time War** Approach for Hand Movement Recognition
A subunit-based Dynamic Time War** (DTW) approach is proposed for hand movement recognition. Two major contributions distinguish the proposed approach from conventional DTW. (1) A set of hand movement subuni...
-
Chapter and Conference Paper
Human Pose Estimation Using Exemplars and Part Based Refinement
In this paper, we proposed a fast and accurate human pose estimation framework that combines top-down and bottom-up methods. The framework consists of an initialization stage and an iterative searching stage. ...
-
Chapter and Conference Paper
Towards Robust Object Detection: Integrated Background Modeling Based on Spatio-temporal Features
We propose a sophisticated method for background modeling based on spatio-temporal features. It consists of three complementary approaches: pixel-level background modeling, region-level one and frame-level one...