29 citations · 123 across the 37 of their papers we have counts for
43 papers
Partition-and-Debias: Agnostic Biases Mitigation via A Mixture of Biases-Specific Experts
Jiaxuan Li, Duc Minh Vo, Hideki Nakayama
Bias mitigation in image classification has been widely researched, and existing methods have yielded notable results. However, most of these methods implicitly assume that a given…
Revisiting Latent Space of GAN Inversion for Real Image Editing
Kai Katsumata, Duc Minh Vo, Bei Liu +1
The exploration of the latent space in StyleGANs and GAN inversion exemplify impressive real-world image editing, yet the trade-off between reconstruction quality and editing quali…
Balancing Reconstruction and Editing Quality of GAN Inversion for Real Image Editing with StyleGAN Prior Latent Space
Kai Katsumata, Duc Minh Vo, Bei Liu +1
The exploration of the latent space in StyleGANs and GAN inversion exemplify impressive real-world image editing, yet the trade-off between reconstruction quality and editing quali…
LED: A Dataset for Life Event Extraction from Dialogs
Yi-Pei Chen, An-Zi Yen, Hen-Hsen Huang +2
Lifelogging has gained more attention due to its wide applications, such as personalized recommendations or memory assistance. The issues of collecting and extracting personal life…
A-CAP: Anticipation Captioning with Commonsense Knowledge
Duc Minh Vo, Quoc-An Luong, Akihiro Sugimoto +1
Humans possess the capacity to reason about the future based on a sparse collection of visual cues acquired over time. In order to emulate this ability, we introduce a novel task c…
Character-Centric Story Visualization via Visual Planning and Token Alignment
Hong Chen, Rujun Han, Te-Lin Wu +2
Story visualization advances the traditional text-to-image generation by enabling multiple image generation based on a complete story. This task requires machines to 1) understand…
StoryER: Automatic Story Evaluation via Ranking, Rating and Reasoning
Hong Chen, Duc Minh Vo, Hiroya Takamura +2
Existing automatic story evaluation methods place a premium on story lexical level coherence, deviating from human preference. We go beyond this limitation by considering a novel \…
Towards Parameter-Efficient Integration of Pre-Trained Language Models In Temporal Video Grounding
Erica K. Shimomoto, Edison Marrese-Taylor, Hiroya Takamura +3
This paper explores the task of Temporal Video Grounding (TVG) where, given an untrimmed video and a natural language sentence query, the goal is to recognize and determine tempora…
Pixel to Binary Embedding Towards Robustness for CNNs
Ikki Kishida, Hideki Nakayama
There are several problems with the robustness of Convolutional Neural Networks (CNNs). For example, the prediction of CNNs can be changed by adding a small magnitude of noise to a…
OSSGAN: Open-Set Semi-Supervised Image Generation
Kai Katsumata, Duc Minh Vo, Hideki Nakayama
We introduce a challenging training scheme of conditional GANs, called open-set semi-supervised image generation, where the training dataset consists of two parts: (i) labeled data…
NOC-REK: Novel Object Captioning with Retrieved Vocabulary from External Knowledge
Duc Minh Vo, Hong Chen, Akihiro Sugimoto +1
Novel object captioning aims at describing objects absent from training data, with the key ingredient being the provision of object vocabulary to the model. Although existing metho…
PPCD-GAN: Progressive Pruning and Class-Aware Distillation for Large-Scale Conditional GANs Compression
Duc Minh Vo, Akihiro Sugimoto, Hideki Nakayama
We push forward neural network compression research by exploiting a novel challenging task of large-scale conditional generative adversarial networks (GANs) compression. To this en…
SciXGen: A Scientific Paper Dataset for Context-Aware Text Generation
Hong Chen, Hiroya Takamura, Hideki Nakayama
Generating texts in scientific papers requires not only capturing the content contained within the given input but also frequently acquiring the external information called \textit…
Graph Energy-based Model for Substructure Preserving Molecular Design
Ryuichiro Hataya, Hideki Nakayama, Kazuki Yoshizoe
It is common practice for chemists to search chemical databases based on substructures of compounds for finding molecules with desired properties. The purpose of de novo molecular…
GraphPlan: Story Generation by Planning with Event Graph
Hong Chen, Raphael Shu, Hiroya Takamura +1
Story generation is a task that aims to automatically produce multiple sentences to make up a meaningful story. This task is challenging because it requires high-level understandin…
Commonsense Knowledge Aware Concept Selection For Diverse and Informative Visual Storytelling
Hong Chen, Yifei Huang, Hiroya Takamura +1
Visual storytelling is a task of generating relevant and interesting stories for given image sequences. In this work we aim at increasing the diversity of the generated stories whi…
Graph-based Heuristic Search for Module Selection Procedure in Neural Module Network
Yuxuan Wu, Hideki Nakayama
Neural Module Network (NMN) is a machine learning model for solving the visual question answering tasks. NMN uses programs to encode modules' structures, and its modularized archit…
MADGAN: unsupervised Medical Anomaly Detection GAN using multiple adjacent brain MRI slice reconstruction
Changhee Han, Leonardo Rundo, Kohei Murao +7
Unsupervised learning can discover various unseen abnormalities, relying on large-scale unannotated medical images of healthy subjects. Towards this, unsupervised methods reconstru…
Meta Approach to Data Augmentation Optimization
Ryuichiro Hataya, Jan Zdenek, Kazuki Yoshizoe +1
Data augmentation policies drastically improve the performance of image recognition tasks, especially when the policies are optimized for the target data and tasks. In this paper,…
Single Model Ensemble using Pseudo-Tags and Distinct Vectors
Ryosuke Kuwabara, Jun Suzuki, Hideki Nakayama
Model ensemble techniques often increase task performance in neural networks; however, they require increased time, memory, and management effort. In this study, we propose a novel…
Bridging the gap between AI and Healthcare sides: towards developing clinically relevant AI-powered diagnosis systems
Changhee Han, Leonardo Rundo, Kohei Murao +2
Despite the success of Convolutional Neural Network-based Computer-Aided Diagnosis research, its clinical applications remain challenging. Accordingly, developing medical Artificia…
Empirical Study of Easy and Hard Examples in CNN Training
Ikki Kishida, Hideki Nakayama
Deep Neural Networks (DNNs) generalize well despite their massive size and capability of memorizing all examples. There is a hypothesis that DNNs start learning from simple pattern…
Faster AutoAugment: Learning Augmentation Strategies using Backpropagation
Ryuichiro Hataya, Jan Zdenek, Kazuki Yoshizoe +1
Data augmentation methods are indispensable heuristics to boost the performance of deep neural networks, especially in image recognition tasks. Recently, several studies have shown…
Latent-Variable Non-Autoregressive Neural Machine Translation with Deterministic Inference Using a Delta Posterior
Raphael Shu, Jason Lee, Hideki Nakayama +1
Although neural machine translation models reached high translation quality, the autoregressive nature makes inference difficult to parallelize and leads to high translation latenc…