5 papers
LLM-Driven Completeness and Consistency Evaluation for Cultural Heritage Data Augmentation in Cross-Modal Retrieval
Jian Zhang, Junyi Guo, Junyi Yuan +5
Cross-modal retrieval is essential for interpreting cultural heritage data, but its effectiveness is often limited by incomplete or inconsistent textual descriptions, caused by his…
EditGarment: An Instruction-Based Garment Editing Dataset Constructed with Automated MLLM Synthesis and Semantic-Aware Evaluation
Deqiang Yin, Junyi Guo, Huanda Lu +2
Instruction-based garment editing enables precise image modifications via natural language, with broad applications in fashion design and customization. Unlike general editing task…
HiGarment: Cross-modal Harmony Based Diffusion Model for Flat Sketch to Realistic Garment Image
Junyi Guo, Jingxuan Zhang, Fangyu Wu +5
Diffusion-based garment synthesis tasks primarily focus on the design phase in the fashion domain, while the garment production process remains largely underexplored. To bridge thi…
Hubness Reduction with Dual Bank Sinkhorn Normalization for Cross-Modal Retrieval
Zhengxin Pan, Haishuai Wang, Fangyu Wu +2
The past decade has witnessed rapid advancements in cross-modal retrieval, with significant progress made in accurately measuring the similarity between cross-modal pairs. However,…
Towards Cross-modal Retrieval in Chinese Cultural Heritage Documents: Dataset and Solution
Junyi Yuan, Jian Zhang, Fangyu Wu +3
China has a long and rich history, encompassing a vast cultural heritage that includes diverse multimodal information, such as silk patterns, Dunhuang murals, and their associated…