Henrique MORIMITSU 恩瑞

Lecturer at the School of Computer & Communication Engineering

University of Science and Technology Beijing

Biography

Henrique Morimitsu is a member of the PRIR lab, where he works with Prof. Xiaobin Zhu and Prof. Xu-Cheng Yin. His research interests are mainly in the field of video motion estimation, especially focused on developing efficient and cost-effective methods.

Interests

Computer Vision
Deep Learning
Optical Flow
Object Tracking

Education

PhD in Computer Science, 2015

University of São Paulo
MSc in Computer Science, 2011

University of São Paulo
BSc in Information Systems, 2008

University of São Paulo

News

UrbanAccess 2024 paper

Our paper “Tactile Path Guidance via Weakly Supervised Visual Attention” has been accepted to the The 4th Annual Workshop on The Future of Urban Accessibility (Oct 24, 2024, online).

Oct 21, 2024

ICRA 2024 paper

Our paper “RAPIDFlow: Recurrent Adaptable Pyramids with Iterative Decoding for Efficient Optical Flow Estimation” has been accepted to the IEEE International Conference on Robotics and Automation (May 13-17, 2024, Yokohama, Japan).

Mar 7, 2024

AAAI 2024 paper

Our paper “Recurrent Partial Kernel Network for Efficient Optical Flow Estimation” has been accepted to The 38th Annual AAAI Conference on Artificial Intelligence (February 20-27, 2024, Vancouver, Canada).

Dec 14, 2023

Projects

DAISY GPU

An implementation of the DAISY descriptor using deep learning libraries (PyTorch and Tensorflow).

Moku Zero

An implementation of Alpha Zero to solve the Moku game (Gomoku, Connect4, Tic-Tac-Toe). Strong pretrained models are available.

Proposal Selection Tracking

Official source code for the Online Object Tracking with Proposal Selection, ICCV 2015 paper.

PTLFlow

PyTorch Lightning platform for training and testing state-of-the-art Optical Flow models.

SIFT-Flow GPU

An implementation of the SIFT-Flow descriptor using PyTorch.

similarpapers.com

A web interface to browse and find suggestions of similar papers in CV, ML, and AI conferences.

Recent Publications

Quickly discover relevant content by filtering publications.

Suayder M. Costa, Rafael J. P. Damaceno, Henrique Morimitsu, Roberto M. Cesar-Jr. (2024). Tactile Path Guidance via Weakly Supervised Visual Attention. In UrbanAccess.

PDF Cite

Henrique Morimitsu, Xiaobin Zhu, Roberto M. Cesar-Jr., Xiangyang Ji, Xu-Cheng Yin (2024). RAPIDFlow: Recurrent Adaptable Pyramids with Iterative Decoding for Efficient Optical Flow Estimation. In ICRA.

PDF Cite Code Video

Henrique Morimitsu, Xiaobin Zhu, Xiangyang Ji, Xu-Cheng Yin (2024). Recurrent Partial Kernel Network for Efficient Optical Flow Estimation. In AAAI.

PDF Cite Code Video DOI

Chunyu Xie, Heng Cai, Jincheng Li, Fanjing Kong, Xiaoyu Wu, Jianfei Song, Henrique Morimitsu, Lin Yao, Dexin Wang, Xiangzheng Zhang, Dawei Leng, Baochang Zhang, Xiangyang Ji, Yafeng Deng (2023). CCMB: A Large-scale Chinese Cross-modal Benchmark. In ACM MM.

PDF Cite Code Dataset DOI

Chunyu Xie, Jincheng Li, Heng Cai, Fanjing Kong, Xiaoyu Wu, Jianfei Song, Henrique Morimitsu, Lin Yao, Dexin Wang, Dawei Leng, Baochang Zhang, Xiangyang Ji, Yafeng Deng (2022). Zero and R2D2: A large-scale Chinese cross-modal benchmark and A vision-language framework. ArXiv.

PDF Cite Code Dataset

See all publications