Junji Otsuka

According to our database, Junji Otsuka authored at least 16 papers between 2012 and 2026.

Collaborative distances:

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

2026

Structuring Open-Ended NAS: Semi-Automated Design Knowledge Structuring with LLMs for Efficient Neural Architecture Search.

Yuiko Sakuma, Masakazu Yoshimura, Marcel Gröpl, Zitang Sun, Junji Otsuka, Atsushi Irie, Takeshi Ohashi

CoRR, May, 2026

LLM as a Tool, Not an Agent: Code-Mined Tree Transformations for Neural Architecture Search.

Masakazu Yoshimura, Zitang Sun, Yuiko Sakuma, Junji Otsuka, Atsushi Irie, Takeshi Ohashi

CoRR, April, 2026

2025

Online Data Curation for Object Detection via Marginal Contributions to Dataset-level Average Precision.

Zitang Sun, Masakazu Yoshimura, Junji Otsuka, Atsushi Irie, Takeshi Ohashi

CoRR, November, 2025

SemiISP/SemiIE: Semi-Supervised Image Signal Processor and Image Enhancement Leveraging One-to-Many Mapping sRGB-to-RAW.

Masakazu Yoshimura, Junji Otsuka, Radu Berdan, Takeshi Ohashi

CoRR, April, 2025

RAW-Diffusion: RGB-Guided Diffusion Models for High-Fidelity RAW Image Generation.

Christoph Reinders, Radu Berdan, Beril Besbinar, Junji Otsuka, Daisuke Iso

Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2025

ReRAW: RGB-to-RAW Image Reconstruction via Stratified Sampling for Efficient Object Detection on the Edge.

Radu Berdan, Beril Besbinar, Christoph Reinders, Junji Otsuka, Daisuke Iso

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2025

2024

Multi Positive Contrastive Learning with Pose-Consistent Generated Images.

Sho Inayoshi, Aji Resindra Widya, Satoshi Ozaki, Junji Otsuka, Takeshi Ohashi

CoRR, 2024

Mixed-precision Supernet Training from Vision Foundation Models using Low Rank Adapter.

Yuiko Sakuma, Masakazu Yoshimura, Junji Otsuka, Atsushi Irie, Takeshi Ohashi

CoRR, 2024

PQDynamicISP: Dynamically Controlled Image Signal Processor for Any Image Sensors Pursuing Perceptual Quality.

Masakazu Yoshimura, Junji Otsuka, Takeshi Ohashi

CoRR, 2024

2023

Self-Supervised Reversed Image Signal Processing via Reference-Guided Dynamic Parameter Selection.

Junji Otsuka, Masakazu Yoshimura, Takeshi Ohashi

CoRR, 2023

DynamicISP: Dynamically Controlled Image Signal Processor for Image Recognition.

Masakazu Yoshimura, Junji Otsuka, Atsushi Irie, Takeshi Ohashi

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

Rawgment: Noise-Accounted RAW Augmentation Enables Recognition in a Wide Variety of Environments.

Masakazu Yoshimura, Junji Otsuka, Atsushi Irie, Takeshi Ohashi

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

2022

Efficient Joint Detection and Multiple Object Tracking with Spatially Aware Transformer.

Siddharth Sagar Nijhawan, Leo Hoshikawa, Atsushi Irie, Masakazu Yoshimura, Junji Otsuka, Takeshi Ohashi

CoRR, 2022

2014

Evolutionary Fuzzy Rule Construction for Iterative Object Segmentation.

Junji Otsuka, Tomoharu Nagao

Proceedings of the ICAART 2014, 2014

2013

An Improvement in Classification Accuracy of Fuzzy Oriented Classifier Evolution.

Junji Otsuka, Tomoharu Nagao

Proceedings of the IEEE International Conference on Systems, 2013

2012

Flexible design of image classification rules using extended Fuzzy Oriented Classifier Evolution.

Junji Otsuka, Tomoharu Nagao

Proceedings of the 6th International Conference on Soft Computing and Intelligent Systems (SCIS), 2012