Yu-Wen Tseng

Hi, I'm Yu-Wen Tseng

a Ph.D. student in the Department of Computer Science & Information Engineering at NTU. I'm a member of the AIMM research group in CMLab, advised by Wen-Huang Cheng and Hong-Han Shuai. My work centers on advancing vision-centric perception for driving environments, specifically in the domains of semantic occupancy prediction and test-time adaptation when facing unknown scenes.

News

Resume

Publications

  1. J.-Y. Jiang-Lin, K.-Y. Huang, L. Zou, L. Lo, S.-P. Yang, Y.-W. Tseng, K.-H. Lin, C.-L. Chen, Y.-T. Ta, Y.-T. Wang, P.-C. Chen, H.-X. Xie, H.-H. Shuai, and W.-H. Cheng. “TriDF: Evaluating Perception, Detection, and Hallucination for Interpretable DeepFake Detection.” CVPR 2026. [Paper] [Project]
  2. K.-H. Lin, Y.-W. Tseng, K.-Y. Huang, J.-C. Wu, and W.-H. Cheng. “InstructFLIP: Exploring Unified Vision-Language Model for Face Anti-spoofing.” ACM MM 2025. [Paper] [Project] [Code]
  3. S.-P. Yang, Y.-W. Tseng, Y.-C. Yang, I.-B. Liao, C.-E. Huang, S.-H. Liu, Y.-H. Li, J.-C. Wu, H.-H. Shuai, and W.-H. Cheng. “Unraveling Vanishing Point and Calibrating Tiny Object for Semantic Scene Completion.” ICIP 2025.
  4. Y.-W. Tseng, S.-P. Yang, J.-C. Wu, I.-B. Liao, Y.-H. Li, H.-H. Shuai, and W.-H. Cheng. “Memory-augmented Re-completion for 3D Semantic Scene Completion.” AAAI 2025. [Paper] [Code]
  5. H.-I. Liu, Y.-W. Tseng, K. C. Chang, P. J. Wang, H. H. Shuai, and W.-H. Cheng. “A DeNoising FPN with Transformer R-CNN for Tiny Object Detection.” IEEE Trans. Geoscience and Remote Sensing, 2024. [Paper] [Code]
  6. H.-X. Xie, C.-J. Peng, Y.-W. Tseng, H.-J. Chen, C.-F. Hsu, H.-H. Shuai, and W.-H. Cheng. “EmoVIT: Revolutionizing Emotion Insights with Visual Instruction Tuning.” CVPR 2024. [Paper] [Code]
  7. Y.-W. Tseng, H.-H. Shuai, C.-C. Huang, Y.-H. Li, and W.-H. Cheng. “Language-Guided Negative Sample Mining for Open-Vocabulary Object Detection.” ICEIC 2024. [Paper]
  8. W.-H. Ke, Y.-W. Tseng, and W.-H. Cheng. “Task-Specific Pruning: Efficient Parameter Reduction in Multi-task Object Detection Models.” APSIPA ASC 2023.