26 citations · 50 across the 18 of their papers we have counts for
21 papers
The Implicit Bias of Hyperbolic Representation Learning for Multiclass Data: A Busemann Risk Perspective
Xingrun Li, Sho Kuno, Yusuke Mukuta +2
We study the implicit bias of Riemannian gradient flow for hyperbolic multiclass classification with fixed class prototypes in hyperbolic space . Our framework accomm…
Representation Learning: An Intrinsic Mixed-Curvature Space with Higher Curvature Capacities and Deeper Order-Aware Composition
Xingrun Li, Yusuke Mukuta, Xin Yang +2
Mixed-curvature representation learning seeks to capture rich geometric structures that cannot be adequately modeled by a single curvature regime. Existing approaches largely rely…
Linear Fusion MultiDiffusion for Fast Training-Free Spherical Panorama Generation
Akio Hayakawa, Yusuke Mukuta, Tatsuya Harada
We propose LF-MultiDiffusion, a training-free panorama generation method that extends MultiDiffusion to support linear projections between target and reference image spaces. Our ke…
DEJIMA: A Novel Large-scale Japanese Dataset for Image Captioning and Visual Question Answering
Toshiki Katsube, Taiga Fukuhara, Kenichiro Ando +3
This work addresses the scarcity of high-quality, large-scale resources for Japanese Vision-and-Language (V&L) modeling. We present a scalable and reproducible pipeline that integr…
Improved 3D Scene Stylization via Text-Guided Generative Image Editing with Region-Based Control
Haruo Fujiwara, Yusuke Mukuta, Tatsuya Harada
Recent advances in text-driven 3D scene editing and stylization, which leverage the powerful capabilities of 2D generative models, have demonstrated promising outcomes. However, ch…
Style-NeRF2NeRF: 3D Style Transfer From Style-Aligned Multi-View Images
Haruo Fujiwara, Yusuke Mukuta, Tatsuya Harada
We propose a simple yet effective pipeline for stylizing a 3D scene, harnessing the power of 2D image diffusion models. Given a NeRF model reconstructed from a set of multi-view im…
Fully Spiking Denoising Diffusion Implicit Models
Ryo Watanabe, Yusuke Mukuta, Tatsuya Harada
Spiking neural networks (SNNs) have garnered considerable attention owing to their ability to run on neuromorphic devices with super-high speeds and remarkable energy efficiencies.…
The Sound Demixing Challenge 2023 $\unicode{x2013}$ Music Demixing Track
Giorgio Fabbro, Stefan Uhlich, Chieh-Hsin Lai +24
This paper summarizes the music demixing (MDX) track of the Sound Demixing Challenge (SDX'23). We provide a summary of the challenge setup and introduce the task of robust music so…
HiPerformer: Hierarchically Permutation-Equivariant Transformer for Time Series Forecasting
Ryo Umagami, Yu Ono, Yusuke Mukuta +1
It is imperative to discern the relationships between multiple time series for accurate forecasting. In particular, for stock prices, components are often divided into groups with…
Domain Adaptive Multiple Instance Learning for Instance-level Prediction of Pathological Images
Shusuke Takahama, Yusuke Kurose, Yusuke Mukuta +7
Pathological image analysis is an important process for detecting abnormalities such as cancer from cell images. However, since the image size is generally very large, the cost of…
Self-Supervised Learning for Group Equivariant Neural Networks
Yusuke Mukuta, Tatsuya Harada
This paper proposes a method to construct pretext tasks for self-supervised learning on group equivariant neural networks. Group equivariant neural networks are the models whose st…
Grouped self-attention mechanism for a memory-efficient Transformer
Bumjun Jung, Yusuke Mukuta, Tatsuya Harada
Time-series data analysis is important because numerous real-world tasks such as forecasting weather, electricity consumption, and stock market involve predicting data that vary ov…
SATTS: Speaker Attractor Text to Speech, Learning to Speak by Learning to Separate
Nabarun Goswami, Tatsuya Harada
The mapping of text to speech (TTS) is non-deterministic, letters may be pronounced differently based on context, or phonemes can vary depending on various physiological and stylis…
Computational Storytelling and Emotions: A Survey
Yusuke Mori, Hiroaki Yamane, Yusuke Mukuta +1
Storytelling has always been vital for human nature. From ancient times, humans have used stories for several objectives including entertainment, advertisement, and education. Vari…
K-VQG: Knowledge-aware Visual Question Generation for Common-sense Acquisition
Kohei Uehara, Tatsuya Harada
Visual Question Generation (VQG) is a task to generate questions from images. When humans ask questions about an image, their goal is often to acquire some new knowledge. However,…
Learning from Label Proportions with Instance-wise Consistency
Ryoma Kobayashi, Yusuke Mukuta, Tatsuya Harada
Learning from Label Proportions (LLP) is a weakly supervised learning method that aims to perform instance classification from training data consisting of pairs of bags containing…
COMPASS: a Creative Support System that Alerts Novelists to the Unnoticed Missing Contents
Yusuke Mori, Hiroaki Yamane, Ryohei Shimizu +2
When humans write, they may unintentionally omit some information. Complementing the omitted information using a computer is helpful in providing writing support. Recently, in the…
ViNTER: Image Narrative Generation with Emotion-Arc-Aware Transformer
Kohei Uehara, Yusuke Mori, Yusuke Mukuta +1
Image narrative generation is a task to create a story from an image with a subjective viewpoint. Given the importance of the subjective feelings of writers, readers, and character…
Fully Spiking Variational Autoencoder
Hiromichi Kamata, Yusuke Mukuta, Tatsuya Harada
Spiking neural networks (SNNs) can be run on neuromorphic devices with ultra-high speed and ultra-low energy consumption because of their binary and event-driven nature. Therefore,…
Hyperbolic Neural Networks++
Ryohei Shimizu, Yusuke Mukuta, Tatsuya Harada
Hyperbolic spaces, which have the capacity to embed tree structures without distortion owing to their exponential volume growth, have recently been applied to machine learning to b…
Invariant Feature Coding using Tensor Product Representation
Yusuke Mukuta, Tatsuya Harada
In this study, a novel feature coding method that exploits invariance for transformations represented by a finite group of orthogonal matrices is proposed. We prove that the group-…