Ryo Hachiuma  

 



  ![](/sites/default/files/person/Ryo.Hachiuma.jpg)

  

 Ryo Hachiuma is a Research Scientist at NVIDIA Research Taiwan, working on Multi-Modal AI. He received his Ph.D. degree from Keio University, advised by Prof. Hideo Saito. Before joining NVIDIA Research, he was a computer vision engineer at Konica Minolta, Inc. in Japan, working on human action recognition. His research interest is mainly in Human activity analysis from multi-sensory data (e.g., audio-visual, audio-visual-language).



   Research Area(s)

[Artificial Intelligence and Machine Learning ](/research-area/machine-learning-artificial-intelligence)

[Computer Vision](/research-area/computer-vision)

 

 

  

 Main Field of Interest

[Artificial Intelligence and Machine Learning ](/research-area/machine-learning-artificial-intelligence)

 

  

 Google Scholar

[https://scholar.google.co.jp/citations?user=W1KPqGEAAAAJ&hl](https://scholar.google.co.jp/citations?user=W1KPqGEAAAAJ&hl)

 

  

 

 

 



 ### Publications

 

### 2024 

[From Descriptive Richness to Bias: Unveiling the Dark Side of Generative Image Caption Enrichment](/publication/2024-11_descriptive-richness-bias-unveiling-dark-side-generative-image-caption)

Yusuke Hirota, [Ryo Hachiuma](/person/ryo-hachiuma), [Huck Yang](/person/huck-yang), Yuta Nakashima



[EMNLP](https://arxiv.org/pdf/2406.13912)