Shuhei Tarashima

According to our database, Shuhei Tarashima authored at least 18 papers between 2013 and 2026.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of five.

2026

TruncProof: A Guardrail for LLM-based JSON Generation under Token-Length Constraints.

Yoshio Kato, Shuhei Tarashima

CoRR, May, 2026

2025

ViLAaD: Enhancing "Attracting and Dispersing" Source-Free Domain Adaptation with Vision-and-Language Model.

Shuhei Tarashima, Xinqi Shu, Norio Tagawa

CoRR, March, 2025

Efficient 3D Human Pose and Shape Estimation Using Group-Mix Attention in Transformer Models.

Yushan Wang, Shuhei Tarashima, Norio Tagawa

Proceedings of the 20th International Joint Conference on Computer Vision, 2025

RacketDB: A Comprehensive Dataset for Badminton Racket Detection.

Muhammad Abdul Haq, Shuhei Tarashima, Norio Tagawa

Proceedings of the 20th International Joint Conference on Computer Vision, 2025

Oriented Racket Database (ORDB): An Annotated Dataset for Rotated Racket Detection in Badminton.

Muhammad Abdul Haq, Xinqi Shu, Turrnum Shahzadi, Botao Zhang, Shuhei Tarashima, Norio Tagawa

Proceedings of the 8th International ACM Workshop on Multimedia Content Analysis in Sports, 2025

On the Use of Hierarchical Vision Foundation Models for Low-Cost Human Mesh Recovery and Pose Estimation.

Shuhei Tarashima, Yushan Wang, Norio Tagawa

Proceedings of the IEEE/CVF International Conference on Computer Vision, ICCV 2025, 2025

2024

Plug-and-Play Acceleration of Occupancy Grid-based NeRF Rendering using VDB Grid and Hierarchical Ray Traversal.

Yoshio Kato, Shuhei Tarashima

CoRR, 2024

2023

BiLMa: Bidirectional Local-Matching for Text-based Person Re-identification.

Takuro Fujii, Shuhei Tarashima

Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023

Widely Applicable Strong Baseline for Sports Ball Detection and Tracking.

Shuhei Tarashima, Muhammad Abdul Haq, Yushan Wang, Norio Tagawa

Proceedings of the 34th British Machine Vision Conference 2023, 2023

2021

Sports Field Recognition Using Deep Multi-task Learning.

Shuhei Tarashima

J. Inf. Process., 2021

Object Hypotheses as Points for Efficient Multi-Object Tracking.

Shuhei Tarashima

Proceedings of the 16th International Joint Conference on Computer Vision, 2021

One-Shot Deep Model for End-to-End Multi-Person Activity Recognition.

Shuhei Tarashima

Proceedings of the 32nd British Machine Vision Conference 2021, 2021

2019

SFLNet: Direct Sports Field Localization via CNN-Based Regression.

Shuhei Tarashima

Proceedings of the Pattern Recognition - 5th Asian Conference, 2019

2018

Unsupervised Object Proposal Using Depth Boundary Density and Density Uniformity.

Takashi Hosono, Shuhei Tarashima, Jun Shimamura, Tetsuya Kinebuchi

Proceedings of the 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2018

Keypoint Matching for Non-Rigid Object via Locally Consistent Visual Pattern Mining.

Shuhei Tarashima, Jun Shimamura, Tetsuya Kinebuchi, Shin'ichi Satah

Proceedings of the 2018 IEEE International Conference on Image Processing, 2018

2017

Cross-modal transfer with neural word vectors for image feature learning.

Go Irie, Taichi Asami, Shuhei Tarashima, Takayuki Kurozumi, Tetsuya Kinebuchi

Proceedings of the 2017 IEEE International Conference on Acoustics, 2017

2016

Joint object discovery and segmentation with image-wise reconstruction error.

Shuhei Tarashima, Jingjing Pan, Go Irie, Takayuki Kurozumi, Tetsuya Kinebuchi

Proceedings of the 2016 IEEE International Conference on Image Processing, 2016

2013

Fast image/video collection summarization with local clustering.

Shuhei Tarashima, Go Irie, Ken Tsutsuguchi, Hiroyuki Arai, Yukinobu Taniguchi

Proceedings of the ACM Multimedia Conference, 2013