耿佳佳

[15级] 深度学习工程师【京东北京】 2015级 计算机科学与技术
毕业签约京东(北京),中国互联网知名企业(top 10) [1] J. Geng, X. Liu*, Y.M. Cheung, "Audio-visual Speaker Recognition via Multi-modal Correlated Neural Networks", in Proc. IEEE/WIC/ACM International Conference on Web Intelligence Workshops, pp. 123-128, 2016. [2] 柳欣, 耿佳佳, 钟必能,杜吉祥, “多生物特征融合发展现状及其展望”, 小型微型计算机系统, 2017,Vol. 38 (8): 1792-1799. [3] Efficient Speaker Naming via Deep Audio-Face Fusion and End-to-End Attention Model, Asian Conference on Pattern Recognition (ACPR), 2017, 405-410.