1.5k citations · 2.1k across the 48 of their papers we have counts for
48 papers
World Food Atlas Project
Ali Rostami, Z Xie, A Ishino +3
A coronavirus pandemic is forcing people to be "at home" all over the world. In a life of hardly ever going out, we would have realized how the food we eat affects our bodies. What…
Open-Set Domain Adaptation with Visual-Language Foundation Models
Qing Yu, Go Irie, Kiyoharu Aizawa
Unsupervised domain adaptation (UDA) has proven to be very effective in transferring knowledge obtained from a source domain with labeled data to a target domain with unlabeled dat…
Manga109Dialog: A Large-scale Dialogue Dataset for Comics Speaker Detection
Yingxuan Li, Kiyoharu Aizawa, Yusuke Matsui
The expanding market for e-comics has spurred interest in the development of automated methods to analyze comics. For further understanding of comics, an automated approach is need…
LoCoOp: Few-Shot Out-of-Distribution Detection via Prompt Learning
Atsuyuki Miyai, Qing Yu, Go Irie +1
We present a novel vision-language prompt learning approach for few-shot out-of-distribution (OOD) detection. Few-shot OOD detection aims to detect OOD images from classes that are…
Guided Image Synthesis via Initial Image Editing in Diffusion Model
Jiafeng Mao, Xueting Wang, Kiyoharu Aizawa
Diffusion models have the ability to generate high quality images by denoising pure Gaussian noise images. While previous research has primarily focused on improving the control of…
GL-MCM: Global and Local Maximum Concept Matching for Zero-Shot Out-of-Distribution Detection
Atsuyuki Miyai, Qing Yu, Go Irie +1
Zero-shot out-of-distribution (OOD) detection is a task that detects OOD images during inference with only in-distribution (ID) class names. Existing methods assume ID images conta…
Comprehensive Comparisons of Uniform Quantization in Deep Image Compression
Koki Tsubota, Kiyoharu Aizawa
In deep image compression, uniform quantization is applied to latent representations obtained by using an auto-encoder architecture for reducing bits and entropy coding. Quantizati…
Non-uniform Sampling Strategies for NeRF on 360{\textdegree} images
Takashi Otonari, Satoshi Ikehata, Kiyoharu Aizawa
In recent years, the performance of novel view synthesis using perspective images has dramatically improved with the advent of neural radiance fields (NeRF). This study proposes tw…
Rethinking Rotation in Self-Supervised Contrastive Learning: Adaptive Positive or Negative Data Augmentation
Atsuyuki Miyai, Qing Yu, Daiki Ikami +2
Rotation is frequently listed as a candidate for data augmentation in contrastive learning but seldom provides satisfactory improvements. We argue that this is because the rotated…
Universal Deep Image Compression via Content-Adaptive Optimization with Adapters
Koki Tsubota, Hiroaki Akutsu, Kiyoharu Aizawa
Deep image compression performs better than conventional codecs, such as JPEG, on natural images. However, deep image compression is learning-based and encounters a problem: the co…
Saliency-based Multiple Region of Interest Detection from a Single 360° image
Yuuki Sawabe, Satoshi Ikehata, Kiyoharu Aizawa
360° images are informative -- it contains omnidirectional visual information around the camera. However, the areas that cover a 360° image is much larger than the human's field of…
Evaluating the Stability of Deep Image Quality Assessment With Respect to Image Scaling
Koki Tsubota, Hiroaki Akutsu, Kiyoharu Aizawa
Image quality assessment (IQA) is a fundamental metric for image processing tasks (e.g., compression). With full-reference IQAs, traditional IQAs, such as PSNR and SSIM, have been…
COO: Comic Onomatopoeia Dataset for Recognizing Arbitrary or Truncated Texts
Jeonghun Baek, Yusuke Matsui, Kiyoharu Aizawa
Recognizing irregular texts has been a challenging topic in text recognition. To encourage research on this topic, we provide a novel comic onomatopoeia dataset (COO), which consis…
SVG Vector Font Generation for Chinese Characters with Transformer
Haruka Aoki, Kiyoharu Aizawa
Designing fonts for Chinese characters is highly labor-intensive and time-consuming. While the latest methods successfully generate the English alphabet vector font, despite the hi…
Distortion-Aware Self-Supervised 360° Depth Estimation from A Single Equirectangular Projection Image
Yuya Hasegawa, Ikehata Satoshi, Kiyoharu Aizawa
360° images are widely available over the last few years. This paper proposes a new technique for single 360° image depth prediction under open environments. Depth prediction from…
Field-of-View IoU for Object Detection in 360° Images
Miao Cao, Satoshi Ikehata, Kiyoharu Aizawa
360° cameras have gained popularity over the last few years. In this paper, we propose two fundamental techniques -- Field-of-View IoU (FoV-IoU) and 360Augmentation for object dete…
Noisy Annotation Refinement for Object Detection
Jiafeng Mao, Qing Yu, Yoko Yamakata +1
Supervised training of object detectors requires well-annotated large-scale datasets, whose production is costly. Therefore, some efforts have been made to obtain annotations in ec…
NTIRE 2021 Challenge on Perceptual Image Quality Assessment
Jinjin Gu, Haoming Cai, Chao Dong +47
This paper reports on the NTIRE 2021 challenge on perceptual image quality assessment (IQA), held in conjunction with the New Trends in Image Restoration and Enhancement workshop (…
A Novel Perspective for Positive-Unlabeled Learning via Noisy Labels
Daiki Tanaka, Daiki Ikami, Kiyoharu Aizawa
Positive-unlabeled learning refers to the process of training a binary classifier using only positive and unlabeled data. Although unlabeled data can contain positive data, all unl…
What If We Only Use Real Datasets for Scene Text Recognition? Toward Scene Text Recognition With Fewer Labels
Jeonghun Baek, Yusuke Matsui, Kiyoharu Aizawa
Scene text recognition (STR) task has a common practice: All state-of-the-art STR models are trained on large synthetic data. In contrast to this practice, training STR models only…
Building Movie Map -- A Tool for Exploring Areas in a City -- and its Evaluation
Naoki Sugimoto, Yoshihito Ebine, Kiyoharu Aizawa
We propose a new Movie Map system, with an interface for exploring cities. The system consists of four stages; acquisition, analysis, management, and interaction. In the acquisitio…
Few-Shot Font Generation with Deep Metric Learning
Haruka Aoki, Koki Tsubota, Hikaru Ikuta +1
Designing fonts for languages with a large number of characters, such as Japanese and Chinese, is an extremely labor-intensive and time-consuming task. In this study, we addressed…
The Aleatoric Uncertainty Estimation Using a Separate Formulation with Virtual Residuals
Takumi Kawashima, Qing Yu, Akari Asai +2
We propose a new optimization framework for aleatoric uncertainty estimation in regression problems. Existing methods can quantify the error in the target estimation, but they tend…
SLGAN: Style- and Latent-guided Generative Adversarial Network for Desirable Makeup Transfer and Removal
Daichi Horita, Kiyoharu Aizawa
There are five features to consider when using generative adversarial networks to apply makeup to photos of the human face. These features include (1) facial components, (2) intera…