Publications
-
ICCV2025 Workshop LIMIT 2025: Representation Learning with Very Limited Resources: When Data, Modalities, Labels and Computing Resources are Scarce
Intraclass Compactness: A Metric for Evaluating Models Pre-Trained on Various Synthetic Data
Tomoki Suzuki, Kazuki Maeno, Yasunori Ishii and Takayoshi Yamashita
Link: https://openreview.net/attachment?id=G2WCuOVVti&name=pdf
-
20th International Conference on Machine Vision Applications (MVA2025)
Bidirectional Action Sequence Learning for Long-term Action Anticipation with Large Language Models (Best Poster Award)
Yuji Sato, Yasunori Ishii and Takayoshi Yamashita
arXiv: https://arxiv.org/abs/2508.00374 -
The IEEE/CVF Conference on Computer Vision and Pattern Recognition（CVPR2024）
Active Domain Adaptation with False Negative Prediction for Object Detection
Yuzuru Nakamura, Yasunori Ishii and Takayoshi Yamashita
(Highlight Paper)
Link: https://openaccess.thecvf.com/content/CVPR2024/html/Nakamura_Active_Domain_Adaptation_with_False_Negative_Prediction_for_Object_Detection_CVPR_2024_paper.html
Panasonic News Room: [Panasonic Newsroom Global] Panasonic Holdings Focuses on “overlooked data” in AI Models and Develops New Technology Useful for Deploying AI in Multiple Sites -
The IEEE/CVF Conference on Computer Vision and Pattern Recognition（CVPR2024）
Deep Single Image Camera Calibration by Heatmap Regression to Recover Fisheye Images Under Manhattan World Assumption
Nobuhiko Wakai, Satoshi Sato, Yasunori Ishii and Takayoshi Yamashita
Link: https://openaccess.thecvf.com/content/CVPR2024/html/Wakai_Deep_Single_Image_Camera_Calibration_by_Heatmap_Regression_to_Recover_CVPR_2024_paper.html
Project Page: https://github.com/panasonic-ai/manhattan-deep-calib
Panasonic News Room: [Panasonic Newsroom Global] Panasonic Holdings Develops Fisheye Camera Angle Estimation Technology Applying Pose Estimation, Supporting Accurate Positioning and Navigation in Physical Spaces -
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP2024)
hear-your-action: human action recognition by ultrasound active sensing
Risako Tanigawa and Yasunori Ishii
arXiv: https://arxiv.org/abs/2309.08087 -
EEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2024
Learning Intra-Class Multimodal Distributions With Orthonormal Matrices
Jumpei Goto, Yohei Nakata, Kiyofumi Abe, Yasunori Ishii and Takayoshi Yamashita
URL: https://openaccess.thecvf.com/content/WACV2024/html/Goto_Learning_Intra-Class_Multimodal_Distributions_With_Orthonormal_Matrices_WACV_2024_paper.html
Panasonic News Room: [Panasonic Newsroom Global] Panasonic HD Develops Image Recognition AI With New Classification Algorithm That Can Handle Multimodal Distribution -
18th International Conference on Machine Vision Applications (MVA2023)
PALF: Pre-Annotation and Camera-LiDAR Late Fusion for the Easy Annotation of Point Clouds
Yucheng Zhang, Masaki Fukuda, Yasunori Ishii, Kyoko Ohshima and Takayoshi Yamashita
arXiv: https://arxiv.org/abs/2304.08591 -
Asian Conference on Computer Vision (ACCV) 2022
Few-shot Adaptive Object Detection with Cross-Domain CutMix
Yuzuru Nakamura, Yasunori Ishii, Yuki Maruyama and Takayoshi Yamashita
Link: https://openaccess.thecvf.com/content/ACCV2022/html/Nakamura_Few-shot_Adaptive_Object_Detection_with_Cross-Domain_CutMix_ACCV_2022_paper.html
Panasonic News Room: [Panasonic Newsroom Global] Panasonic HD develops new technology that can reduce the cost of data preparation necessary for training AI models -
European Conference on Computer Vision (ECCV) 2022
Rethinking Generic Camera Models for Deep Single Image Camera Calibration to Recover Rotation and Fisheye Distortion
Nobuhiko Wakai, Satoshi Sato, Yasunori Ishii and Takayoshi Yamashita
arXiv: https://arxiv.org/abs/2111.12927
Project page: https://github.com/panasonic-ai/rethinking-generic-camera-models
Panasonic News Room: [Panasonic Newsroom Global] Panasonic Holdings Develops Advanced AI Technology, Accepted to ECCV2022, and IROS2022, Top Conferences in the Field of AI and Robotics -
ECCV2022 Workshop AV4D: Visual Learning of Sounds in Spaces
Invisible-to-Visible: Privacy-Aware Human Segmentation using Airborne Ultrasound via Collaborative Learning Probabilistic U-Net
Risako Tanigawa, Yasunori Ishii, Kazuki Kozuka and Takayoshi Yamashita
arXiv: https://arxiv.org/abs/2205.05293 -
arXiv:2204.07280
Invisible-to-Visible: Privacy-Aware Human Instance Segmentation using Airborne Ultrasound via Collaborative Learning Variational Autoencoder
Risako Tanigawa, Yasunori Ishii, Kazuki Kozuka and Takayoshi Yamashita
arXiv: https://arxiv.org/abs/2204.07280 -
International Conference on Computer Vision(ICCV) Workhop "Interactive Labeling and Data Augmentation for Vision (ILDAV)"
CutDepth:Edge-aware Data Augmentation in Depth Estimation
Yasunori Ishii and Takayoshi Yamashita
arXiv: https://arxiv.org/abs/2107.07684 -
IEEE International Conference on Machine Vision and Applications (MVA) 2021
Lossless AI: Toward Guaranteeing Consistency between Inferences Before and After Quantization via Knowledge Distillation (Best Poster Award)
Tomoyuki Okuno, Yohei Nakata, Yasunori Ishii and Sotaro Tsukizawa
Link: http://www.mva-org.jp/Proceedings/2021/papers/P1-9.pdf -
European Conference on Computer Vision(ECCV) Workshop "The Bright and Dark Sides of Computer Vision: Challenges and Opportunities for Privacy and Security (CV-COPS20)"
Privacy-Aware Face Recognition with Lensless Multi-Pinhole Camera
Yasunori Ishii, Satoshi Sato and Takayoshi Yamashita
Link: https://link.springer.com/chapter/10.1007/978-3-030-68238-5_35 -
International Conference on Computer Vision Theory and Applications (VISAPP) 2020
Simultaneous Visual Context-aware Path Prediction
Haruka Iesaki, Tsubasa Hirakawa, Takayoshi Yamashita, Hironobu Fujiyoshi, Yasunori Ishii, Kazuki Kozuka and Ryota Fujimura
Link: https://www.scitepress.org/Link.aspx?doi=10.5220/0008921307410748 -
IEEE/CVF International Conference on Computer Vision Workshop (ICCVW 2019)
Adherent Raindrop Removal with Self-Supervised Attention Maps and Spatio-Temporal Generative Adversarial Networks
Stefano Alletto, Casey Carlin, Luca Rigazio, Yasunori Ishii and Sotaro Tsukizawa
Link: http://openaccess.thecvf.com/content_ICCVW_2019/papers/ADW/Alletto_Adherent_Raindrop_Removal_with_Self-Supervised_Attention_Maps_and_Spatio-Temporal_Generative_ICCVW_2019_paper.pdf -
NeurIPS Workshop on Systems for ML and Open Source Software
Explain to Fix: A Framework to Interpret and Correct DNN Object Detector Predictions
Denis Gudovskiy, Alec Hodgkinson, Takuya Yamaguchi, Yasunori Ishii and Sotaro Tsukizawa
arXiv: https://arxiv.org/abs/1811.08011 -
3rd IAPR Asian Conference on Pattern Recognition (ACPR) 2015
Deep Learning using Heterogeneous Feature Maps for Maxout Networks
Yasunori Ishii, Reiko Hagawa and Sotaro Tsukizawa
Link: https://ieeexplore.ieee.org/document/7486545 -
3rd IAPR Asian Conference on Pattern Recognition (ACPR) 2015
Multi-staged Deep Learning with Created Coarse and Appended Fine Categories
Reiko Hagawa, Yasunori Ishii and Sotaro Tsukizawa
Link: https://ieeexplore.ieee.org/document/7486461