Page 169 - 《软件学报》2021年第11期

何相腾 等:跨域和跨模态适应学习的无监督细粒度视频分类 3495

[22] Long MS, Zhu H, Wang JM, Jordan MI. Deep transfer learning with joint adaptation networks. In: Proc. of the Int’l Conf. on
Machine Learning (ICML). New York: ACM, 2017. 2208−2217.
[23] He KM, Gkioxari G, Dollár P, Girshick R. Mask R-CNN. In: Proc. of the IEEE Int’l Conf. on Computer Vision (ICCV). Piscataway:
IEEE, 2017. 2980−2988.
[24] Otsu N. A threshold selection method from gray-level histograms. IEEE Trans. on Systems, Man, and Cybernetics (TCYB), 1979,
9(1):62−66.
[25] Wah C, Branson S, Welinder P, Perona P, Belongie S. The Caltech-UCSD birds-200-2011 dataset. Technical Report, CNS-TR-
2011-001, Pasadena: California Institute of Technology, 2011.
[26] Krause J, Stark M, Deng J, Li FF. 3D object representations for fine-grained categorization. In: Proc. of the Int’l Conf. of Computer
Vision Workshop (ICCVW). Piscataway: IEEE, 2013. 554−561.
[27] Zhang WC, Ouyang WL, Li W, Xu D. Collaborative and adversarial network for unsupervised domain adaptation. In: Proc. of the
IEEE Conf. on Computer Vision and Pattern Recognition (CVPR). Piscataway: IEEE, 2018. 3801−3809.
[28] Saito K, Watanabe K, Ushiku Y, Harada T. Maximum classifier discrepancy for unsupervised domain adaptation. In: Proc. of the
IEEE Conf. on Computer Vision and Pattern Recognition (CVPR). Piscataway: IEEE, 2018. 3723−3732.
[29] Carreira J, Zisserman A. Quo Vadis, action recognition? A new model and the kinetics dataset. In: Proc. of the IEEE Conf. on
Computer Vision and Pattern Recognition (CVPR). Piscataway: IEEE, 2017. 4724−4733.

何相腾(1991－),男,博士,主要研究领域为 彭宇新(1974－),男,博士,教授,博士生导
细粒度图像分类,细粒度跨媒体检索,多模 师,CCF 杰出会员,主要研究领域为跨媒体
态内容理解. 分析与推理,图像视频识别与理解,计算机
视觉,人工智能.