Publications

Conference Papers / Preprints

  • T Xiang, A Sun, S Delp, K Kozuka, L Fei-Fei, E Adeli, "Wild2Avatar: Rendering Humans Behind Occlusions", arXiv preprint arXiv:2401.00431, 2023. project website

  • X Wang, S Li, K Kallidromitis, Y Kato, K Kozuka, T Darrell, "Hierarchical open-vocabulary universal image segmentation", arXiv preprint arXiv:2307.00764, 2023. project website

  • H Adachi, T Hirakawa, T Yamashita, H Fujiyoshi, Y Ishii, K Kozuka, "Masking and Mixing Adversarial Training", arXiv preprint arXiv:2302.08066, 2023. pdf

  • S Fujii, Y Ishii, K Kozuka, T Hirakawa, T Yamashita, H Fujiyoshi, "Data Augmentation by Selecting Mixed Classes Considering Distance Between Classes", arXiv preprint arXiv:2209.05122, 2022. pdf

  • A Gokul, K Kallidromitis, S Li, Y Kato, K Kozuka, T Darrell, CJ Reed, "Refine and represent: Region-to-object representation learning", arXiv preprint arXiv:2208.11821, 2022. pdf

  • R Tanigawa, Y Ishii, K Kozuka, T Yamashita, "Invisible-to-Visible: Privacy-Aware Human Segmentation using Airborne Ultrasound via Collaborative Learning Probabilistic U-Net", arXiv preprint arXiv:2205.05293, 2022. pdf

  • R Tanigawa, Y Ishii, K Kozuka, T Yamashita, "Invisible-to-Visible: Privacy-Aware Human Instance Segmentation using Airborne Ultrasound via Collaborative Learning Variational Autoencoder", arXiv preprint arXiv:2204.07280, 2022. pdf

  • D Gudovskiy, S Ishizaka, K Kozuka, "Cflow-ad: Real-time unsupervised anomaly detection with localization via conditional normalizing flows", Proceedings of the IEEE/CVF WACV, 2022. pdf

  • K Kallidromitis, D Gudovskiy, O Iku, L Rigazio, "Contrastive neural processes for self-supervised learning", Asian Conference on Machine Learning, 594-609, 2021. pdf

  • N Wakai, K Kozuka, Y Nakata, S Iida, "Value-Verification Process Proposal for Launching New Services using Image Recognition", Technology, Panasonic Technical Journal 67 (2), 97-101, 2021. pdf

  • N. Rai, H. Chen, J. Ji, R. Desai, K. Kozuka, S. Ishizaka, E. Adeli, J. C. Niebles, "Home Action Genome: Cooperative Compositional Action Understanding", Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition 2021. pdf

  • D. Gudovskiy, L. Rigazio, S. Ishizaka, K. Kozuka, S. Tsukizawa, "AutoDO: Robust AutoAugment for Biased Data with Label Noise via Scalable Probabilistic Implicit Differentiation", Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition 2021. pdf

  • H. Iesaki, T. Hirakawa, T. Yamashita, H. Fujiyoshi, Y. Ishii, K. Kozuka, R. Fujimura, "Simultaneous Visual Context-aware Path Prediction", VISIGRAPP, 2020. pdf

  • K. Kozuka, J. C. Niebles, "Risky Region Localization With Point Supervision", Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 246-253, 2017. pdf

  • K. Kozuka, K. Takata, K. Kondo, K. Karasawa, Y. Hirano, S. Kido, "Development of Automatic Database Registration and Similar-Case Retrieval for Diffuse Lung Diseases by Texture Analysis of Whole-Lung CT Volume", IEEE Engineering in Medicine and Biology Society (EMBC) 2015.

  • Y. Sato, T. Nakada, K. Kozuka, M. Kiyono, T. Nonoyama, M. Kubota, Y. Koie, M. Yasutake, O. Yamamura, "Estimation of Knee Extensor Strength Using Wearable Sensors", IEEE Engineering in Medicine and Biology Society (EMBC) 2015.

  • T. Nakada, Y. Sato, K. Kozuka, M. Kiyono, T. Nonoyama, M. Kubota, Y. Koie, M. Yasutake, O. Yamamura, "Prediction of PeakVO2 from Walking Energy Cost Index for the Elderly", IEEE Engineering in Medicine and Biology Society (EMBC) 2015.

  • K. Kozuka, K. Takata, K. Kondo, M. Kiyono, M. Tanaka, T. Sakai, H. Kimura, "Development of lung CT image retrieval technology using distance metric learning by image findings", 29th International Congress and Exhibition on Computer Assisted Radiology and Surgery (CARS), 2015.

  • Y. Sawada, K. Kozuka, "Transfer Learning Method using Multi-Prediction Deep Boltzmann Machines for a small scale dataset", IAPR Machine Vision And Application Organization (MVA), 2015.

  • H. Kimura, T. Sakai, K. Kondo, K. Takata, K. Kozuka, M. Kiyono, M. Inubushi, M. Toyooka, "A Diagnostic Imaging Education System for Lung CT Images based on Image-Retrieval Technology for Medical Books and DICOM Images", Radiological Society of North America, 2014.

  • Y. Sato, K. Kozuka, Y. Sawada, M. Kiyono, "Learning Multiple Complex Features Based on Classification Results", 22nd International Conference on Pattern Recognition (ICPR2014), pp.3369--3373, 2014.

  • T. Sakai, K. Kondo, K. Takata, K. Kozuka, M. Kiyono, M. Tanaka, H. Kimura, H. Itoh, "Demonstration of a novel diagnosis support system for lung lesions: Computed tomography with an image-retrieval technology based on radiologists knowledge", Radiological Society of North America 99th Scientific Assembly and Annual Meeting, 2013.

  • K. Kozuka., K. Takata., K. Kondo, M. Kiyono, M. Tanaka, T. Sakai, H. Kimura, "Development of lung CT image-retrieval system based on imaging findings and an image-selection interface", The 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 2013.

  • K. Kozuka., K. Takata., K. Kondo, M. Kiyono, M. Tanaka, T. Sakai, H. Kimura, "Development of image-retrieval technology using radiological knowledge extracted from a clinical database of lung CT images", Computer Assisted Radiology and Surgery (CARS) 2013. 27th International Congress and Exhibition, 2013.

  • K. Morikawa, K. Kozuka, S. Adachi, "Assessment of Speech Discrimination Based on the Event-Related Potentials to the Visual Stimuli", IEEE International Conference on Communications (ICC), 2011.

  • K. Kozuka, J. Sato, "Multiple View Geometry for Mixed Dimensional Cameras", VISAPP, 2008.

  • C. Wan, K. Kozuka, J. Sato, "Multiple view geometry for non-rigid motions viewed from translational cameras", Asian Conference on Computer Vision, 2007.

  • K. Kozuka, J. Sato, "Rectification of 3D Data Obtained from Moving Range Sensors by using Multiple View Geometry", ICIAP 2007. 14th International Conference on Image Analysis and Processing, 2007.


  • Journal Papers

  • Y. Sawada, K. Kozuka, "Whole Layers Transfer Learning of Deep Neural Networks for a Small Scale Dataset", International journal of machine learning and computing, 2016. pdf

  • K. Morikawa, K. Kozuka, S. Adachi, "A Proposed Speech Discrimination Assessment Methodology Based on Event-Related Potentials to Visual Stimuli", International Journal of E-Health and Medical Communications (IJEHMC), 2012.

  • K. Kozuka, C. Wan, J. Sato, "Rectification of 3D data obtained from moving range sensor by using extended projective multiple view geometry", International Journal of Automation and Computing, 2008.


  • Invited Talks

  • K. Kozuka, "Panasonic AI's Collaboration with Top Universities", cvpaper.challenge Conference winter 2023FY.

  • K. Kozuka, "Building large scale datasets for AI development", GPU2021.

  • K. Kozuka, "Development of Similar Case Retrieval Technology for Supporting Medical Image Diagnosis and Education of Various Lung Diseases", MI2013.

  • K. Kozuka, "Present situation of image-retrieval technology using clinical database of lung CT images", Computer Assisted Radiology and Surgery(CARS)2013. 27th International Congress and Exhibition, 2013.




  • Academic Activities

    Awards

  • 2024: Best Presentation Award, The Interim Research Presentation of the MBA Service & Hospitality Program, GSM, Kyoto University.

  • 2023: SDGs Special Prize, Mizuho Securities Endowment Award, SDGs Leadership Award 2023.

  • 2015: MVA2015, Best Poster Awards.

  • 2014: Young Researcher Award at JCMI2014

  • 2013: Best Presentation Award at JCMI2013


  • Conference Experience

  • Organizer: International Challenge on Compositional and Multimodal Perception, International Conference on Computer Vision Workshop, 2021, 2023.

  • Organizer: Home Action Genome (HOMAGE) competition in conjunction with ActivityNet, Conference on Computer Vision and Pattern Recognition 2021 Workshop, 2021.

  • Organizer: International Challenge on Compositional and Multimodal Perception, European Conference on Computer Vision Workshop, 2020, 2022.