Low-radiation interventional imaging using video frame interpolation.
Recommended citation: Tang, Z., Xiong, Q., Wu, X., Xu, T., Shi, Y., Xu, X., Xu, J., & Wang, R. (2024). "Radiation Reduction for Interventional Imaging via Video Frame Interpolation." Insights into Imaging, 15(1).
Objective caption evaluation via semantic-equivalent image reconstruction.
Recommended citation: Tang, Z., Qi, J., Tang, K., Zheng, Y., & Huang, J. (2026). "A Reconstruction-Based Framework for Caption Evaluation Beyond Reference Captions." NeurIPS 2026 (under review).
Semantic closed-loop evaluation framework for unified multimodal models.
Recommended citation: Zhang, H., Qi, J., Tang, Z., & Huang, J. (2026). "Do You See What You Draw?" NeurIPS 2026 (under review).
A benchmark decoupling long-context quality from short-video metrics in generative video evaluation.
Recommended citation: Tang, Z., Qi, J., Zhao, B., & Huang, J. (2026). "Long-CODE: Isolating Pure Long-Context as an Orthogonal Dimension in Video Evaluation." ACM MM 2026 (under review).
Dual-reward reinforcement learning for improving multimodal caption completeness and correctness.
Recommended citation: Tang, Z., Wang, L., Qi, J., Jiang, W., Hou, P., Zeng, A., & Huang, J. (2026). "CCCaption: Dual-Reward RL for Complete and Correct Image Captioning." CVPR 2026.
Unified benchmark covering classification, detection, forecasting, and generation for ECG time-series.
Recommended citation: Tang, Z., Qi, J., Zheng, Y., & Huang, J. (2025). "A Comprehensive Benchmark for Electrocardiogram Time-Series." ACM MM 2025.