面向新工科的《视觉媒体编码与通信》课程教学改革探索与实践——融合人工智能前沿技术与工程实践能力培养
Exploration and Practice of Teaching Reform in the Course “Visual Media Coding and Communication” for New Engineering Education—Integrating Cutting-Edge Artificial Intelligence Technologies and Engineering Practice Capability Development
摘要: 人工智能时代视觉媒体的爆发式发展和新工科建设背景对信息工程专业人才的工程实践能力与前沿技术素养提出了新的要求。本论文以信息工程专业选修课《视觉媒体编码与通信》为实践对象,提出“理论筑基–实验强化–前沿拓展”三位一体教学思路。在教学内容上,将端到端深度语义编码、自监督语义表征学习等前沿研究方向融入课堂;在实验体系上,设计了视觉媒体“信号处理–视觉编码–智能感知”递进式综合实验;在教学方法上,引入案例驱动教学方式。实践表明,改革后学生解决实际工程问题的能力得到提升,对前沿技术的兴趣与创新意识明显增强,可为新工科背景下同类课程的教学改革提供参考。
Abstract: The explosive growth of visual media in the era of artificial intelligence and the background of the construction of new engineering education have placed new demands on the engineering practice ability and cutting-edge technology literacy of information engineering professionals. This paper takes the elective course “Visual Media Coding and Communication” in information engineering as the practical object and proposes a three-in-one teaching approach of “theoretical foundation—experimental reinforcement—cutting-edge expansion”. In terms of teaching content, cutting-edge research directions such as end-to-end deep semantic coding and self-supervised semantic representation learning are integrated into the classroom; in terms of experimental system, a progressive comprehensive experiment of visual media “signal processing—visual coding—intelligent perception” is designed; in terms of teaching methods, a case-driven teaching approach is introduced. Practice shows that after the reform, students’ ability to solve practical engineering problems has been improved, and their interest in cutting-edge technologies and innovative awareness has been significantly enhanced, which can provide a reference for the teaching reform of similar courses under the background of new engineering education.
文章引用:毕海霞, 刘威. 面向新工科的《视觉媒体编码与通信》课程教学改革探索与实践——融合人工智能前沿技术与工程实践能力培养[J]. 教育进展, 2026, 16(6): 411-418. https://doi.org/10.12677/ae.2026.1661143

参考文献

[1] 姜晓坤, 朱泓, 李志义. 新工科人才培养新模式[J]. 高教发展与评估, 2018, 34(2): 17-24.
[2] 陈健, 郑雅丹, 林丽. 新工科背景下面向学生的数字图像处理课程案例教学研究[J]. 计算机教育, 2026(4): 302-308.
[3] 何小海, 李鑫磊, 魏海涛, 毕晓东, 聂尧佳, 熊志娜, 张皓彦, 熊淑华. 深度学习驱动的视频编码: 方法、进展与展望[J]. 数据采集与处理, 2026, 41(2): 515-542.
[4] 万帅, 杨付正, 新一代视频压缩标准H.265/HEVC原理、标准与实现[M]. 北京: 电子工业出版社, 2014.
[5] 熊轲, 严祥康, 毛晋, 董瑞. 樊平毅基于自监督学习的多任务图像无源域适应语义通信框架[J/OL]. 北京航空航天大学学报, 1-15. 2026-06-02.[CrossRef
[6] 张垚鑫, 张旻. 基于人工智能背景下应用型本科院校的“数字图像处理”课程教学改革[J]. 教育进展, 2024, 14(12): 1149-1154.
[7] 晏苏红, 谢于晨, 赵红霞. 人工智能赋能《信号与系统》课程教学改革研究[J]. 职业教育发展, 2025, 14(7): 181-187.
[8] 范迪, 孙慧敏, 周钰慧, 滕升华. 数字图像处理的“三融合、三驱动、三协同”课程教学创新实践[J]. 创新教育研究, 2024, 12(9): 271-277.
[9] 纪昕茹, 陈杰, 李鑫, 张博芝. AI赋能移动通信技术课程产教融合教学改革研究与实践[J]. 社会科学前沿, 2026, 15(3): 1-7.
[10] Garg, A., Soodhani, K.N. and Rajendran, R. (2025) Enhancing Data Analysis and Programming Skills through Structured Prompt Training: The Impact of Generative AI in Engineering Education. Computers and Education: Artificial Intelligence, 8, Article ID: 100380. [Google Scholar] [CrossRef
[11] Khatry, K. and Samsami, R. (2025) Engineering Education in the Era of Generative Artificial Intelligence (Gen AI): Current State and Future Directions. 2025 ASEE Northeast Section Conference, Bridgeport, 22 March 2025.
[12] Wang, T.Y., Li, F., Qiao, X.Y., et al. (2021) Low-Complexity Error Resilient HEVC Video Coding: A Deep Learning Approach. IEEE Transactions on Image Processing, 30, 1245-1260. [Google Scholar] [CrossRef] [PubMed]
[13] Mei, Y., Li, L., Li, Z. and Li, F. (2022) Learning-Based Scalable Image Compression with Latent-Feature Reuse and Prediction. IEEE Transactions on Multimedia, 24, 4143-4157. [Google Scholar] [CrossRef
[14] Kuang, Z.Z., Bi, H.X., Li, F., Xu, C. and Sun, J. (2024) Polarimetry-Inspired Contrastive Learning for Class-Imbalanced PolSAR Image Classification. IEEE Transactions on Geoscience and Remote Sensing, 62, Article ID: 5212819. [Google Scholar] [CrossRef
[15] Kuang, Z.Z., Bi, H.X., Li, F. and Xu, C. (2025) ECP-Mamba: An Efficient Multiscale Self-Supervised Contrastive Learning Method with State Space Model for PolSAR Image Classification. IEEE Transactions on Geoscience and Remote Sensing, 63, Article ID: 5218718. [Google Scholar] [CrossRef