张嘉琪，2017年本科毕业于大连理工大学软件学院，2023年博士毕业于中国科学院计算技术研究所，曾在北京大学视频与视觉技术国家工程研究中心从事博士后研究，2026年加入北京大学计算机学院担任特聘副研究员，研究兴趣包括视频编码、多模态数据编码和具身智能等。已发表国际期刊和会议论文40余篇，获国际技术挑战赛冠军3项。主持国家自然科学基金青年科学基金项目、博士后科学基金面上项目、博士后国家资助计划等科研项目，曾获国家科学技术进步奖二等奖、北京市科学技术进步奖一等奖、IEEE标准技术贡献奖、AVS产业技术创新奖等奖励。
代表论文
[1] Jiaqi Zhang, Yunrui Jian, Suhong Wang, Chuanmin Jia, Shanshe Wang, Siwei Ma, and Wen Gao. Textural and Directional Information Based Offset In-Loop Filtering in AVS3[J]. IEEE Transactions on Multimedia (TMM), 2023, 25: 5957–5971.
[2] Jiaqi Zhang, Meng Wang, Chuanmin Jia, Shanshe Wang, Siwei Ma, and Wen Gao. Scalable Intra Coding Optimization for Video Coding[J]. IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2022, 32(10): 7092–7106.
[3] Jiaqi Zhang, Meng Wang, Chuanmin Jia, Qi Wang, Shanshe Wang, Siwei Ma, and Wen Gao. Fast Partition Mode Decision via a Plug-in Fully Connected Network for Video Coding[C]. Data Compression Conference (DCC), 2022: 222–231.
[4] Jiaqi Zhang, Xu Han, Chuanmin Jia, Shanshe Wang, and Siwei Ma. A Hardware-Friendly AVS3 Entropy Decoder Architecture for 8K Ultra-High-Definition Video[C]. Data Compression Conference (DCC), 2025.
[5] Zetian Song, Jiaqi Zhang, Wenhong Duan, Yuhuai Zhang, Xinfeng Zhang, and Siwei Ma. SPC-NeRF: Spatial Predictive Compression for Voxel-Based Radiance Field[J]. ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM), 2026.
[6] Qizhe Wang, Xiaohan Lu, Haocheng Tang, Jiaye Fu, Jiaqi Zhang, and Siwei Ma. WaveletSR: Blind Super-Resolution for Noisy 3D Gaussian Splatting[C]. IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2026.
[7] Zhaoyu Li, Yanchen Zhao, Xu Han, Zhimeng Huang, Siwei Ma, Yun Jiang, and Jiaqi Zhang. Neural-Enhanced Hybrid Video Coding: Learning-Based Motion Modeling and Adaptive In-Loop Filtering[C]. IEEE International Symposium on Circuits and Systems (ISCAS), 2026.
[8] Zetian Song, Jiaye Fu, Jiaqi Zhang, Xiaohan Lu, Chuanmin Jia, Siwei Ma, and Wen Gao. TinySplat: Feedforward Approach for Generating Compact 3D Scene Representation[J]. IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2026.
[9] Longtao Feng, Qian Yin, Jiaqi Zhang, Yuwen He, and Siwei Ma. High Accuracy Rate Control for Neural Video Coding Based on Rate-Distortion Modeling[J]. IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2025.
[10] Yanchen Zhao, Jiaye Fu, Zhimeng Huang, Jiaqi Zhang, and Siwei Ma. RAPNet: Rate-Distortion-Aware Video Pre-Processing via One-Step Reinforcement Learning for Video Coding[J]. IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2026.
[11] Haotian Zhang, Feiyue Long, Yixin Yu, Jian Xue, Haocheng Tang, Tongda Xu, Zhenning Shi, Yan Wang, Siwei Ma, and Jiaqi Zhang. Parallax to Align Them All: An OmniParallax Attention Mechanism for Distributed Multi-View Image Compression[C]. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026.
[12] Xiaohan Lu, Jiaye Fu, Jiaqi Zhang, Zetian Song, Chuanmin Jia, and Siwei Ma. Cross-View-Consistent Feed-Forward 3D Gaussian Splatting for Novel View Synthesis[J]. Pattern Recognition, 2026, 178: 113474.
[13] Jiaye Fu, Qiankun Gao, Chengxiang Wen, Yanmin Wu, Siwei Ma, Jiaqi Zhang, and Jian Zhang. ReCon-GS: Continuum-Preserved Gaussian Streaming for Fast and Compact Reconstruction of Dynamic Scenes[C]. Advances in Neural Information Processing Systems (NeurIPS), 2025.
