Page 213 - 《软件学报》2025年第5期

程浩喆 等: 基于双向拟合掩码重建的多模态自监督点云表示学习 2113

[47] Cheng HZ, Han X, Shi PC, Zhu JH, Li ZY. Multi-trusted cross-modal information bottleneck for 3D self-supervised representation
learning. Knowledge-based Systems, 2024, 283: 111217. [doi: 10.1016/j.knosys.2023.111217]
[48] Wu Y, Liu JM, Gong MG, Gong PR, Fan XL, Qin AK, Miao QG, Ma WP. Self-supervised intra-modal and cross-modal contrastive
learning for point cloud understanding. IEEE Trans. on Multimedia, 2024, 26: 1626–1638. [doi: 10.1109/TMM.2023.3284591]
[49] Anvekar T, Bazazian D. GPr-Net: Geometric prototypical network for point cloud few-shot learning. In: Proc. of the 2023 IEEE/CVF
Conf. on Computer Vision and Pattern Recognition Workshops. Vancouver: IEEE, 2023. 4178–4187. [doi: 10.1109/CVPRW59228.2023.
00440]
[50] Sharma C, Kaul M. Self-supervised few-shot learning on point clouds. In: Proc. of the 34th Int’l Conf. on Neural Information Processing
Systems. 2020. 7212–7221.
[51] Snell J, Swersky K, Zemel R. Prototypical networks for few-shot learning. In: Proc. of the 31st Int’l Conf. on Neural Information
Processing Systems. Long Beach: Curran Associates Inc., 2017. 4080–4090.
[52] Huang TY, Dong BW, Yang YH, Huang XS, Lau RWH, Ouyang WL, Zuo WM. CLIP2Point: Transfer CLIP to point cloud classification
with image-depth pre-training. In: Proc. of the 2023 IEEE/CVF Int’l Conf. on Computer Vision. Paris: IEEE, 2023. 22157–22167. [doi:
10.1109/ICCV51070.2023.02025]
[53] Choy C, Gwak J, Savarese S. 4D spatio-temporal ConvNets: Minkowski convolutional neural networks. In: Proc. of the 2019 IEEE/CVF
Conf. on Computer Vision and Pattern Recognition. Long Beach: IEEE, 2019. 3075–3084. [doi: 10.1109/CVPR.2019.00319]
[54] Ronneberger O, Fischer P, Brox T. U-Net: Convolutional networks for biomedical image segmentation. In: Proc. of the 18th Medical
Image Computing and Computer-assisted Intervention. Munich: Springer, 2015. 234–241. [doi: 10.1007/978-3-319-24574-4_28]
[55] Liu Z, Mao HZ, Wu CY, Feichtenhofer C, Darrell T, Xie SN. A ConvNet for the 2020s. In: Proc. of the 2022 IEEE/CVF Conf. on
Computer Vision and Pattern Recognition. New Orleans: IEEE, 2022. 11976–11986. [doi: 10.1109/CVPR52688.2022.01167]
[56] Kirillov A, Girshick R, He KM, Dollár P. Panoptic feature pyramid networks. In: Proc. of the 2019 IEEE/CVF Conf. on Computer Vision
and Pattern Recognition. Long Beach: IEEE, 2019. 6399–6408. [doi: 10.1109/CVPR.2019.00656]
[57] Xiao TT, Liu YC, Zhou BL, Jiang YN, Sun J. Unified perceptual parsing for scene understanding. In: Proc. of the 15th European Conf. on
Computer Vision. Munich: Springer, 2018. 418–434. [doi: 10.1007/978-3-030-01228-1_26]

附中文参考文献:
[1] 朱向雷, 王海弛, 尤翰墨, 张蔚珩, 张颖异, 刘爽, 陈俊洁, 王赞, 李克秋. 自动驾驶智能系统测试研究综述. 软件学报, 2021, 32(7):
2056–2077. http://www.jos.org.cn/1000-9825/6266.htm [doi: 10.13328/j.cnki.jos.006266]
[2] 闫涛, 高浩轩, 张江峰, 钱宇华, 张临垣. 分组并行的轻量化实时微观三维形貌重建方法. 软件学报, 2024, 35(4): 1717–1731. http://
www.jos.org.cn/1000-9825/7013.htm [doi: 10.13328/j.cnki.jos.007013]
[36] 陈浩楠, 朱映映, 赵骏骐, 田奇. 基于多模态关系建模的三维形状识别方法. 软件学报, 2024, 35(5): 2208–2219. http://www.jos.org.cn/
1000-9825/7026.htm [doi: 10.13328/j.cnki.jos.007026]

程浩喆(1997－), 男, 博士生, 主要研究领域为深 胡乃文(2000－), 男, 硕士生, 主要研究领域为深
度学习, 三维计算机视觉. 度学习, 三维计算机视觉.

祝继华(1982－), 男, 博士, 教授, 博士生导师, 谢奕凡(2001－), 男, 硕士生, 主要研究领域为深

CCF 高级会员, 主要研究领域为计算机视觉, 机 度学习, 三维计算机视觉.

器学习.

史鹏程(1998－), 男, 硕士生, 主要研究领域为深 李仕奇(2000－), 男, 硕士生, 主要研究领域为深

度学习, 三维视计算机觉. 度学习, 三维计算机视觉.