李胜曦 - 北京航空航天大学 - 电子信息工程学院

个人简介

长期致力于图像信号建模、表征和压缩的理论及应用技术研究，攻克图像视频信号的强鲁棒建模、高质量表征和低码率压缩关键技术，突破智能图像信号处理技术发展面临的噪声多、标注少以及传输难困境。在IEEE Trans. Pattern Anal. Mach. Intell.（TPAMI）等SCI Q1/Q2期刊以及Advances in Neural Information Processing Systems（NeurIPS/NIPS）、IEEE Conference on Computer Vision and Pattern Recognition（CVPR）等CCF会议发表论文30余篇。研究成果在国际标准化ISO、ITU组织多项最新标准中得到应用，服务于全球图像/视频信号压缩、传输与处理业务。获Lee Family奖、中国优秀自费留学生奖。入选国家级青年人才计划。

研究领域

视频压缩、图像处理、概率生成模型、表征学习

近期论文

查看导师最新文章（温馨提示：请注意重名现象，建议点开原文通过作者单位确认）

概率表征模型 Shengxi Li*, Zeyang Yu, Min Xiang, and Danilo Mandic, "Reciprocal GAN through Characteristic Functions (RCF-GAN)", IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 45(2):2246-2263, 2023. Shengxi Li*, Zeyang Yu, Min Xiang, and Danilo Mandic, "Reciprocal Adversarial Learning via Characteristic Functions", Advances in Neural Information Processing Systems (NeurIPS/NIPS), 33: 217-228, 2020. 【Spotlight】 Mai Xu*, Shengxi Li, Jianhua Lu, Wenwu Zhu. "Compressibility Constrained Sparse Representation with Learnt Dictionary for Low Bit-rate Image Compression", IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 24(10): 1743-1757, 2014. 【获最佳论文提名】图像与视频压缩 Lai Jiang, Yifei Li, Shengxi Li*, Mai Xu*, Se Lei, Yichen Guo, and Bo Huang, "Does Text Attract Attention on E-commerce Images: A Novel Saliency Prediction Dataset and Method", IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022. Shengxi Li, Mai Xu*, Yun Ren, and Zulin Wang. "Closed-form Optimization on Saliency-guided Image Compression for HEVC-MSP", IEEE Transactions on Multimedia (TMM), 20(1):155-170, 2018. Shengxi Li, Mai Xu*, Zulin Wang, and Xiaoyan Sun, "Optimal Bit Allocation for CTU Level Rate Control in HEVC", IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 27(11): 2409-2424, 2017. 概率模型与优化 Shengxi Li*, and Danilo Mandic, "Von Mises-Fisher Elliptical Distribution", IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2023. Shengxi Li*, Zeyang Yu, and Danilo Mandic, "A Universal Framework for Learning the Elliptical Mixture Model", IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 32(7): 3181-3195, 2021. Shengxi Li*, Zeyang Yu, Min Xiang, and Danilo Mandic, "Solving General Elliptical Mixture Models through an Approximate Wasserstein Manifold", AAAI Conference on Artificial Intelligence (AAAI), 34(04): 4658-4666, 2020. 【Oral】