Conferences (English)

2025

    1. 2D Motion Generation Using Joint Spatial Information with 2CM-GPT
      Ryota Inoue, Tsubasa Hirakawa, Takayoshi Yamashita, and Hironobu Fujiyoshi
      In International Conference on Computer Vision Theory and Applications (VISAPP), 2025
    2. Deep Learning, Driver’s Assistance System, Vision and Language Model, Evaluation Method
      Masaki Nambata, Tsubasa Hirakawa, Takayoshi Yamashita, Hironobu Fujiyoshi, and 3 more authors
      In International Conference on Computer Vision Theory and Applications (VISAPP), 2025
    3. Grade Prediction Using fastText Features Weighted Through Differential Pattern Mining
      Ryota Tachi, Tsubasa Hirakawa, Takayoshi Yamashita, and Hironobu Fujiyoshi
      In International Conference on Learning Analytics & Knowledge, 2025
    4. An Investigation of the Relationship between Open-Ended Questionnaires and Lectures
      Masaki Koike, Tsubasa Hirakawa, Takayoshi Yamashita, and Hironobu Fujiyoshi
      In International Conference on Learning Analytics & Knowledge, 2025

    2024

    1. ECCV
      Layer-Wise Relevance Propagation with Conservation Property for ResNet
      Seitaro Otsuki, Tsumugi Iida, Félix Doublet, Tsubasa Hirakawa, and 3 more authors
      In European Conference on Computer Vision (ECCV), 2024
    2. Enhancing the Accuracy of Predicting Students Grades in Open-Ended Questions through Adjustments to Attention Weights
      Masaki Koike, Hirokazu Kohama, Tsubasa Hirakawa, Takayoshi Yamashita, and 1 more author
      In International Conference on Educational Data Mining (EDM), 2024
    3. ACCV
      Faster convergence and Uncorrelated gradients in Self-Supervised Online Continual Learning
      Koyo Imai, Naoto Hayashi, Tsubasa Hirakawa, Takayoshi Yamashita, and 2 more authors
      In Asian Conference on Computer Vision (ACCV), 2024
    4. ACCV
      DeBiFormer: Vision Transformer with Deformable Agent Bi-level Routing Attention
      NguyenHuu BaoLong, Chenyu Zhang, Yuzhi Shi, Tsubasa Hirakawa, and 3 more authors
      In Asian Conference on Computer Vision (ACCV), 2024
    5. Binary-Decomposed Vision Transformer: Compressing and Accelerating Vision Transformer by Binary Decomposition
      Ryota Kondo, Hiroaki Minoura, Tsubasa Hirakawa, Takayoshi Yamashita, and 1 more author
      In IEEE International Conference on Image Processing (ICIP), 2024
    6. Larval Hostplant Prediction from Luehdorfia japonica Image using Multi-label ABN
      Tsubasa Hirakawa, Takaaki Arai, Takayoshi Yamashita, Hironobu Fujiyoshi, and 3 more authors
      In ECCV Workshop on Computer Vision for Ecology, 2024
    7. Potential Risk Localization via Weak Labeling out of Blind Spot
      Kota Shimomura, Tsubasa Hirakawa, Takayoshi Yamashita, and Hironobu Fujiyoshi
      In CVPR Workshop on Autonomous Driving, 2024
    8. High-Precision for Multi-Task Learning from In-Vehicle Camera using BiFPN
      Chenyu Zhang, Hidenori Itaya, Tsubasa Hirakawa, Takayoshi Yamashita, and 1 more author
      In IEEE Intelligent Vehicle Symposium (IV), 2024
    9. Human-like Guidance by Generating Navigation Using Spatial-Temporal Scene Graph
      Hayato Suzuki, Kota Shimomura, Tsubasa Hirakawa, Takayoshi Yamashita, and 4 more authors
      In IEEE Intelligent Vehicle Symposium (IV), 2024
    10. Auxiliary selection: optimal selection of auxiliary tasks using deep reinforcement learning
      Hidenori Itaya, Tsubasa Hirakawa, Takayoshi Yamashita, and Hironobu Fujiyoshi
      In IIEEJ International Conference on Image Electronics and Visual Computing (IEVC), 2024
    11. Class Weighted Focal Loss for Improving Class Imbalance in Semi-supervised Object Detection
      Shinichi Hoketsu, Tsubasa Hirakawa, Takayoshi Yamashita, and Hironobu Fujiyoshi
      In International Conference on Computer Vision Theory and Applications (VISAPP), 2024
    12. Diverse Data Selection Considering Data Distribution for Unsupervised Continual Learning
      Naoto Hayashi, Tsubasa Hirakawa, Takayoshi Yamashita, and Hironobu Fujiyoshi
      In International Conference on Computer Vision Theory and Applications (VISAPP), 2024

      2023

      1. Recommending Learning Actions Using Neural Network
        Hirokazu Kohama, Yuki Ban, Tsubasa Hirakawa, Takayoshi Yamashita, and 3 more authors
        In International Conference on Computers in Education, 2023
      2. BMVC
        Embedding Human Knowledge into Spatio-Temproal Attention Branch Network in Video Recognition via Temporal attention
        Saki Noguchi, Yuzhi Shi, Tsubasa Hirakawa, Takayoshi Yamashita, and 1 more author
        In British Machine Vision Conference (BMVC), 2023
      3. Data Drift Detection with KS Test using Attention Map
        Tsunemi Nitta, Yuzhi Shi, Tsubasa Hirakawa, Takayoshi Yamashita, and 1 more author
        In Asian Conference on Pattern Recognition (ACPR), 2023
      4. Single-Shot Pruning for Pre-trained Models: Rethinking the Importance of Magnitude Pruning
        Hirokazu Kohama, Hiroaki Minoura, Tsubasa Hirakawa, Takayoshi Yamashita, and 1 more author
        In ICCV Workshop on Resource Efficient Deep Learning for Computer Vision, 2023
      5. Human-like Guidance with Gaze Estimation and Classification-based Text Generation
        Masaki Nambata, Kota Shimomura, Tsubasa Hirakawa, Takayoshi Yamashita, and 1 more author
        In IEEE International Conference on Intelligent Transportation Systems (ITSC), 2023
      6. Visual Explanation for Cooperative Behavior in Multi-Agent Reinforcement Learning
        Hidenori Itaya, Tom Sagawa, Tsubasa Hirakawa, Takayoshi Yamashita, and 1 more author
        In International Joint Conference on Neural Networks (IJCNN), 2023
      7. Analyzing the Accuracy, Representations, and Explainability of Various Loss Functions for Deep Learning
        Tenshi Ito, Hiroki Adachi, Tsubasa Hirakawa, Takayoshi Yamashita, and 1 more author
        In International Joint Conference on Neural Networks (IJCNN), 2023
      8. Potential Risk Estimation with Single Monocular Camera
        Kota Shimomura, Hiroki Adachi, Tsubasa Hirakawa, Takayoshi Yamashita, and 3 more authors
        In CVPR workshop on Secure and Safe Autonomous Driving (SSAD), 2023
      9. Learning from AI: An Interactive Learning Method Using a DNN Model Incorporating Expert Knowledge as a Teacher
        Kohei Hattori, Hironobu Fujiyoshi, Takayoshi Yamashita, and Tsubasa Hirakawa
        In International Conference on Artificial Intelligence in Education (AIED), 2023
      10. ICLR
        This Looks Like It Rather Than That: ProtoKNN For Similarity-Based Classifiers
        Yuki Ukai, Tsubasa Hirakawa, Takayoshi Yamashita, and Hironobu Fujiyoshi
        In International Conference on Learning Representations (ICLR), 2023
      11. Complement Objective Mining Branch for Optimizing Attention Map
        Takaaki Iwayoshi, Hiroki Adachi, Tsubasa Hirakawa, Takayoshi Yamashita, and 1 more author
        In International Conference on Computer Vision Theory and Applications (VISAPP), 2023
      12. Masking and Mixing Adversarial Training
        Hiroki Adachi, Tsubasa Hirakawa, Takayoshi Yamashita, Hironobu Fujiyoshi, and 2 more authors
        In International Conference on Computer Vision Theory and Applications (VISAPP), 2023
      13. Understanding of Feature Representation in Convolutional Neural Networks and Vision Transformer
        Hiroaki Minoura, Tsubasa Hirakawa, Takayoshi Yamashita, and Hironobu Fujiyoshi
        In International Conference on Computer Vision Theory and Applications (VISAPP), 2023
      14. 1D-SalsaSAN: Semantic Segmentation of LiDAR Point Cloud with Self-Attention
        Takahiro Suzuki, Tsubasa Hirakawa, Takayoshi Yamashita, and Hironobu Fujiyoshi
        In International Conference on Computer Vision Theory and Applications (VISAPP), 2023

        2022

        1. Solving the Deadlock Problem with Deep Reinforcement Learning Using Information from Multiple Vehicles
          Tsuyoshi Goto, Hidenori Itaya, Tsubasa Hirakawa, Takayoshi Yamashita, and 1 more author
          In IEEE Intelligent Vehicles Symposium (IV), 2022
        2. Quantification of mimicry resemblance in butterflies using feature extractor of deep neural network
          Kai Amino, Tsubasa Hirakawa, Masaya Yago, and Takashi Matsuo
          In Congress of Europian Society for Evolutionary Biology (ESEB), 2022
        3. Forest-Related SDG Issues Monitoring for Data-Scarce Regions Employing Machine Learning and Remote Sensing - A Case Study for Ena City, Japan
          Anh Phan, Kiyoshi Takejima, Tsubasa Hirakawa, and Hiromichi Fukui
          In IEEE International Geoscience and Remote Sensing Symposium (IGARSS), 2022
        4. Collision Prediction and Visual Explanation Generation Using Structural Knowledge in Object Placement Tasks
          Haruka Matsuo, Shumpei Hatahaka, Arisa Ueda, Tsubasa Hirakawa, and 3 more authors
          In IROS, late breaking results poster, 2022
        5. ACCV
          Visual Explanation Generation Based on Lambda Attention Branch Networks
          Tsumugi Iida, Takumi Komatsu, Kanta Kaneda, Tsubasa Hirakawa, and 3 more authors
          In Asian Conference on Computer Vision (ACCV), 2022
        6. ECCV
          Deep Ensemble Learning by Diverse Knowledge Distillation for Fine-Grained Object Classification
          Naoki Okamoto, Tsubasa Hirakawa, Takayoshi Yamashita, and Hironobu Fujiyoshi
          In European Conference on Computer Vision, 2022
          arXiv Code
        7. Class-Wise FM-NMS for Knowledge Distillation of Object Detection
          Lyuzhuang Liu, Tsubasa Hirakawa, Takayoshi Yamashita, and Hironobu Fujiyoshi
          In IEEE International Conference on Image Processing (ICIP), 2022
        8. Action Spotting in Soccer Videos Using Multiple Scene Encoders
          Yuzhi Shi, Hiroaki Minoura, Takayoshi Yamashita, Tsubasa Hirakawa, and 4 more authors
          In International Conference on Pattern Recognition (ICPR), 2022
        9. Refining Design Spaces in Knowledge Distillation for Deep Collaborative Learning
          Sachi Iwata, Soma Minami, Tsubasa Hirakawa, Takayoshi Yamashita, and 1 more author
          In International Conference on Pattern Recognition (ICPR), 2022

          2021

          1. Performance Prediction and Importance Analysis Using Transformer
            Akiyoshi Satake, Hironobu Fujiyoshi, Takayoshi Yamashita, Tsubasa Hirakawa, and 1 more author
            In International Conference on Computers in Education Conference (ICCE), 2021
          2. 1D Self-Attention Network for Point Cloud Semantic Segmentation Using Omnidirectional LiDAR
            Takahiro Suzuki, Tsubasa Hirakawa, Takayoshi Yamashita, and Hironobu Fujiyoshi
            In Asian Conference on Pattern Recognition (ACPR), 2021
          3. Super-Class Mixup for Adjusting Training Data
            Shungo Fujii, Naoki Okamoto, Toshiki Seo, Tsubasa Hirakawa, and 2 more authors
            In Asian Conference on Pattern Recognition (ACPR), 2021
          4. IROS
            Iterative Coarse-to-Fine 6D-Pose Estimation Using Back-propagation
            Ryosuke Araki, Kohsuke Mano, Tadanori Hirano, Tsubasa Hirakawa, and 2 more authors
            In 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2021
          5. Multi-Domain Semantic-Segmentation using Multi-Head Model
            Shota Masaki, Tsubasa Hirakawa, Takayoshi Yamashita, and Hironobu Fujiyoshi
            In IEEE International Intelligent Transportation Systems Conference (ITSC), 2021
          6. Semantic Segmentation And Change Detection By Multi-Task U-Net
            Shungo Tsutsui, Tsubasa Hirakawa, Takayoshi Yamashita, and Hironobu Fujiyoshi
            In IEEE International Conference on Image Processing (ICIP), 2021
          7. Action Spotting and Temporal Attention Analysis in Soccer Videos
            Hiroaki Minoura, Tsubasa Hirakawa, Takayoshi Yamashita, Hironobu Fujiyoshi, and 3 more authors
            In International Conference on Machine Vision and Applications (MVA), 2021
          8. Attention Mining Branch for Optimizing Attention Map
            Takaaki Iwayoshi, Masahiro Mitsuhara, Masayuki Takada, Tsubasa Hirakawa, and 2 more authors
            In International Conference on Machine Vision and Applications (MVA), 2021
          9. Relational Subgraph for Graph-based Path Prediction
            Masaki Miyata, Katsutoshi Shiraki, Hiroaki Minoura, Tsubasa Hirakawa, and 2 more authors
            In International Conference on Machine Vision and Applications (MVA), 2021
          10. Visual Explanation using Attention Mechanism in Actor-Critic-based Deep Reinforcement Learning
            Hidenori Itaya, Tsubasa Hirakawa, Takayoshi Yamashita, Hironobu Fujiyoshi, and 1 more author
            In International Joint Conference on Neural Networks (IJCNN), 2021
            arXiv
          11. Image Captioning for Near-Future Events from Vehicle Camera Images and Motion Information
            Yuki Mori, Tsubasa Hirakawa, Takayoshi Yamashita, and Hironobu Fujiyoshi
            In IEEE Intelligent Vehicles Symposium (IV), 2021
          12. 3D Object Detection with Normal-map on Point Clouds
            Jishu Miao., Tsubasa Hirakawa., Takayoshi Yamashita., and Hironobu Fujiyoshi.
            In VISAPP, 2021
          13. Embedding Human Knowledge into Deep Neural Network via Attention Map
            Masahiro Mitsuhara., Hiroshi Fukui., Yusuke Sakashita., Takanori Ogata., and 3 more authors
            In VISAPP, 2021
            arXiv
          14. Collaborative Learning of Generative Adversarial Networks
            Takuya Tsukahara, Tsubasa Hirakawa, Takayoshi Yamashita, and Hironobu Fujiyoshi
            In VISAPP, 2021

            2020

            1. Correction of Seasonal Effects on VIIRS DNB Monthly Composites by Using Stable Lit Data and Regression Convolutional Neural Network
              Chuc Man Duc, Tsubasa Hirakawa, and Hiromichi Fukui
              In IEEE International Geoscience and Remote Sensing Symposium (IGARSS), 2020
            2. Improving reliability of attention branch network by introducing uncertainty
              Takuya Tsukahara, Tsubasa Hirakawa, Takayoshi Yamashita, and Hironobu Fujiyoshi
              In International Conference on Pattern Recognition (ICPR), 2020
            3. ACCV
              Knowledge Transfer Graph for Deep Collaborative Learning
              Soma Minami, Tsubasa Hirakawa, Takayoshi Yamashita, and Hironobu Fujiyoshi
              In Asian Conference on Computer Vision (ACCV), 2020
              arXiv Code
            4. ACCV
              Spatial Temporal Attention Graph Convolutional Networks with Mechanics-Stream for Skeleton-Based Action Recognition
              Katsutoshi Shiraki, Tsubasa Hirakawa, Takayoshi Yamashita, and Hironobu Fujiyoshi
              In Asian Conference on Computer Vision (ACCV), 2020
            5. Video Object Detection and Tracking based on Angle Consistency between Motion and Flow
              Toshiki Seo, Tsubasa Hirakawa, Takayoshi Yamashita, and Hironobu Fujiyoshi
              In IEEE Intelligent Vehicles Symposium (IV), 2020
            6. ICRA
              MT-DSSD: Deconvolutional Single Shot Detector Using Multi Task Learning for Object Detection, Segmentation, and Grasping Detection
              Ryosuke Araki, Takeshi Onishi, Tsubasa Hirakawa, Takayoshi Yamashita, and 1 more author
              In IEEE International Conference on Robotics and Automation (ICRA), 2020
            7. Simultaneous Visual Context-aware Path Prediction
              Haruka Iesaki, Tsubasa Hirakawa, Takayoshi Yamashita, Hironobu Fujiyoshi, and 3 more authors
              In VISAPP, 2020
            8. Acquisition of Optimal Connection Patterns for Skeleton-based Action Recognition with Graph Convolutional Networks
              Katsutoshi Shiraki., Tsubasa Hirakawa., Takayoshi Yamashita., and Hironobu Fujiyoshi.
              In VISAPP, 2020

              2019

              1. Coarse-to-Fine Deep Orientation Estimator for Local Image Matching
                Yasuaki Mori, Tsubasa Hirakawa, Takayoshi Yamashita, and Hironobu Fujiyoshi
                In Asian Conference on Pattern Recognition (ACPR), 2019
              2. Attention Neural Baby Talk: Captioning of Risk Factors while Driving
                Yuki Mori, Hiroshi Fukui, Tsubasa Hirakawa, Jo Nishiyama, and 2 more authors
                In IEEE Intelligent Transportation Systems Conference (ITSC), 2019
              3. Automatic Creation of Path Information on Digital Map
                Haruka Iesaki, Shuhei Naruse, Tsubasa Hirakawa, Takayoshi Yamashita, and 2 more authors
                In IEEE Intelligent Transportation Systems Conference (ITSC), 2019
              4. Adaptive Selection of Auxiliary Tasks in UNREAL
                Hidenori Itaya, Tsubasa Hirakawa, Takayoshi Yamasita, and Hironobu Fujiyoshi
                In IJCAI Workshop on 2nd Scaling-Up Reinforcement Learning (SURL), 2019
              5. CVPR
                Attention Branch Network: Learning of Attention Mechanism for Visual Explanation
                Hiroshi Fukui, Tsubasa Hirakawa, Takayoshi Yamashita, and Hironobu Fujiyoshi
                In Computer Vision and Pattern Recognition (CVPR), 2019
                arXiv Code
              6. Visual Explanation by Attention Branch Network for End-to-end Learning-based Self-driving
                Keisuke Mori, Hiroshi Fukui, Takuya Murase, Tsubasa Hirakawa, and 2 more authors
                In IEEE Intelligent Vehicles Symposium (IV), 2019
              7. Scene Context-aware Rapidly-exploring Random Trees for Global Path Planning
                Tsubasa Hirakawa, Takayoshi Yamashita, and Hironobu Fujiyoshi
                In International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops), 2019
              8. Path Predictions using Object Attributes and Semantic Environment
                Hiroaki Minoura., Tsubasa Hirakawa., Takayoshi Yamashita., and Hironobu Fujiyoshi.
                In International Conference on Computer Vision Theory and Applications (VISAPP), 2019
              9. Improved Activity Forecasting for Generating Trajectories
                Daisuke Ogawa, Toru Tamaki, Tsubasa Hirakawa, Bisser Raytchev, and 2 more authors
                In The Korea-Japan joint workshop on Frontiers of Computer Vision (FCV), 2019
                arXiv

                2018

                1. Survey on Vision-Based Path Prediction
                  Tsubasa Hirakawa, Takayoshi Yamashita, Toru Tamaki, and Hironobu Fujiyoshi
                  In International Conference on Human-Computer Interaction (HCII), 2018
                  arXiv

                  2017

                  1. Travel Time-Dependent Maximum Entropy Inverse Reinforcement Learning for Seabird Trajectory Prediction
                    Tsubasa Hirakawa, Takayoshi Yamashita, Ken Yoda, Toru Tamaki, and 1 more author
                    In Asian Conference on Pattern Recognition (ACPR), 2017

                    2016

                    1. Discriminative Subtree Selection for NBI Endoscopic Image Labeling
                      Tsubasa Hirakawa, Toru Tamaki, Takio Kurita, Bisser Raytchev, and 7 more authors
                      In ACCV workshop on Mathematical and Computational Methods in Biomedical Imaging and Image Analysis, 2016
                    2. Transfer Learning for Endoscopic Image Classification
                      Shoji Sonoyama, Toru Tamaki, Tsubasa Hirakawa, Bisser Raytchev, and 5 more authors
                      In The Korea-Japan joint workshop on Frontiers of Computer Vision (FCV), 2016
                      arXiv
                    3. Computer-Aided Colorectal Tumor Classification in NBI Endoscopy Using CNN Features
                      Tamaki Toru, Shoji Sonoyama, Tsubasa Hirakawa, Bisser Raytchev, and 5 more authors
                      In The Korea-Japan joint workshop on Frontiers of Computer Vision (FCV), 2016
                      arXiv

                      2015

                      1. Transfer learning for Bag-of-Visual words approach to NBI endoscopic image classification
                        Shoji Sonoyama, Tsubasa Hirakawa, Toru Tamaki, Takio Kurita, and 6 more authors
                        In IEEE Engineering in Medicine and Biology Society (EMBC), 2015
                      2. Trade-off between speed and performance for colorectal endoscopic NBI image classification
                        Shoji Sonoyama, Toru Tamaki, Tsubasa Hirakawa, Bisser Raytchev, and 5 more authors
                        In SPIE Medical Imaging, 2015

                        2014

                        1. SVM-MRF segmentation of colorectal NBI endoscopic images
                          Tsubasa Hirakawa, Tom Tamaki, Bisser Raytchev, Kazufumi Kaneda, and 4 more authors
                          In IEEE Engineering in Medicine and Biology Society (EMBC), 2014

                          2013

                          1. Smoothing posterior probabilities with a particle filter of dirichlet distribution for stabilizing colorectal NBI endoscopy recognition
                            Tsubasa Hirakawa, Toru Tamaki, Bisser Raytchev, Kazufumi Kaneda, and 6 more authors
                            In IEEE International Conference on Image Processing (ICIP), 2013
                          2. Labeling colorectal NBI zoom-videoendoscope image sequences with MRF and SVM
                            Tsubasa Hirakawa, Toru Tamaki, Bisser Raytchev, Kazufumi Kaneda, and 6 more authors
                            In IEEE Engineering in Medicine and Biology Society (EMBC), 2013