18 citations · 35 across the 7 of their papers we have counts for
7 papers
Guidelines for External Disturbance Factors in the Use of OCR in Real-World Environments
Kenji Iwata, Eiki Ishidera, Toshifumi Yamaai +6
The performance of OCR has improved with the evolution of AI technology. As OCR continues to broaden its range of applications, the increased likelihood of interference introduced…
Estimation of Human Condition at Disaster Site Using Aerial Drone Images
Tomoki Arai, Kenji Iwata, Kensho Hara +1
Drones are being used to assess the situation in various disasters. In this study, we investigate a method to automatically estimate the damage status of people based on their acti…
Can Vision Transformers Learn without Natural Images?
Kodai Nakashima, Hirokatsu Kataoka, Asato Matsumoto +2
Can we complete pre-training of Vision Transformers (ViT) without natural images and human-annotated labels? Although a pre-trained ViT seems to heavily rely on a large-scale datas…
Describing and Localizing Multiple Changes with Transformers
Yue Qiu, Shintaro Yamamoto, Kodai Nakashima +4
Change captioning tasks aim to detect changes in image pairs observed before and after a scene change and generate a natural language description of the changes. Existing change ca…
Dominant Codewords Selection with Topic Model for Action Recognition
Hirokatsu Kataoka, Masaki Hayashi, Kenji Iwata +3
In this paper, we propose a framework for recognizing human activities that uses only in-topic dominant codewords and a mixture of intertopic vectors. Latent Dirichlet allocation (…
Semantic Change Detection with Hypermaps
Teppei Suzuki, Soma Shirakabe, Yudai Miyashita +3
Change detection is the study of detecting changes between two different images of a scene taken at different times. By the detected change areas, however, a human cannot understan…
Feature Evaluation of Deep Convolutional Neural Networks for Object Recognition and Detection
Hirokatsu Kataoka, Kenji Iwata, Yutaka Satoh
In this paper, we evaluate convolutional neural network (CNN) features using the AlexNet architecture and very deep convolutional network (VGGNet) architecture. To date, most CNN r…