CLIP-SegFusion: An Attention-Guided Feature Fusion Framework for Multi-Level Detection on AI-Generated Artworks.

@inproceedings{zheng-2026-clipsegfusion, author = {Yuqian Zheng and Hyeongjin Ahn and Juyeob Lee and Eunil Park}, editor = {Stevan Rudinac and Zi Huang and Marcel Worring and Lucia Vadicamo and Xirong Li and Pascal Mettes and Lizi Liao}, title = {{CLIP-SegFusion: An Attention-Guided Feature Fusion Framework for Multi-Level Detection on AI-Generated Artworks}}, booktitle = {{Proceedings of the 2026 International Conference on Multimedia Retrieval, ICMR 2026, Amsterdam, The Netherlands, June 16-19, 2026}}, pages = {2486--2495}, publisher = {ACM}, year = {2026}, url = {https://doi.org/10.1145/3805622.3810639}, doi = {https://doi.org/10.1145/3805622.3810639} }