Author

Yu-Heng Li

h-index 6 View on Semantic Scholar

We have 3 of 34 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Open access Sep 2026

CineScope-Fuse: Cross-Scale Semantic Fusion for Cinematic Aesthetic Assessment of Multimodal-LLM-Generated Videos

Multimodal large language models and diffusion transformers have made text-to-video generation accessible to film production, advertising and social-media editing, but the assessment of generated video aesthetics remains poorly aligned with how viewers diagnose cinematic failure. A video may be sharp at the frame level...

Yan-Xiu Dan, Yu-Heng Li · Applied Sciences · 0 citations

Open access Jul 2026

DFA-Det: Dynamic Feature Augmentation and Hierarchical Adaptive Fusion for Small Object Detection in Low-Altitude Complex Scenes

Experiments show that DFA-Det improves small-object precision, crowded-scene recall, and cross-scale robustness compared with representative two-stage, one-stage, transformer-based, and recent YOLO-family detectors.

Donghang Li, Yu-Heng Li · Processes · 0 citations

Open access Jul 2026

TopoGraph-Fusion: Hierarchical Task-Conditioned Topology Reasoning for RGB–Thermal Object Detection

TopoGraph-Fusion is presented, a hierarchical graph-guided dual-modal object detector that formulates fusion as topology-aware reasoning rather than direct feature concatenation and improves small-object recall, cross-modal consistency, and robustness under modality imbalance.

Pu Yu, Yanshan Ma, Yu-Heng Li et al. · Symmetry · 0 citations