Acknowledgement
이 논문은 2024년도 정부(과학기술정보통신부)의 재원으로 정보통신기획평가원의 지원을 받아 수행된 연구임 (No.2021-0-02068, 인공지능 혁신 허브 연구개발)
References
- Jabeen, S. et al, A review on methods and applications in multimodal deep learning. TOMM, 19, 2s, pp.1-41, 2023.
- Stahlschmidt, S.R. et al, Multimodal deep learning for biomedical data fusion: a review, Briefings in Bioinformatics, 23, 2, p.bbab569, 2022.
- Radford, A. et al, Learning transferable visual models from natural language supervision, PMLRICML, 2021, pp. 8748-8763.
- Hager, P. et al, Best of both worlds: Multimodal contrastive learning with tabular and imaging data, CVPR, Vancouver, 2023, pp. 23924-23935.
- Friedland, G et al, The Handbook of Multimodal-Multisensor Interfaces: Language Processing, Software, Commercialization, and Emerging Directions-Volume 3, New York, ACM, pp. 659-704.
- Dwork, C., Differential privacy, ICALP, Berlin, 2006, pp. 1-12).
- Mironov, I, Renyi differential privacy, IEEECSF, Santa Barbara, 2017, pp. 263-275.
- Busa-Fekete, R.I. et al, Label differential privacy and private training data release, PMLRICML, Hawaii, 2023, pp. 3233-3251.
- Cai, C. et al, A multimodal differential privacy framework based on fusion representation learning, Connection Science, 34, 1, pp.2219-2239, 2022.
- Caron, M. et al, Emerging properties in self-supervised vision transformers. ICCV, 2021, Montreal, pp. 9650-9660.
- Caron, M. et al, Unsupervised learning of visual features by contrasting cluster assignments. NeurIPS, 2020, pp. 9912-9924.
- Zolfaghari, M. et al, Crossclr: Cross-modal contrastive learning for multi-modal video representations. CVPR, 2021, pp. 1450-1459.
- Ghazi, B. et al, Deep learning with label differential privacy, NeurIPS, 2021, pp.27131-27145.
- Huang, J. et al, DVM-CAR: A large-scale automotive dataset for visual marketing research and application, IEEE Big Data, Osaka, 2022, pp. 4140-4147.