Cross-Domain Sequential Recommendation (CDSR) predicts user behavior by leveraging historical interactions across multiple domains, focusing on modeling cross-domain preferences through intra- and inter-sequence item relationships. Inspired by human cognitive processes, we propose Hierarchical Attention Fusion of Visual and Textual Representations (HAF-VT), a novel approach integrating visual and textual data to enhance cognitive modeling. Using the frozen CLIP model, we generate image and text embeddings, enriching item representations with multimodal data. A hierarchical attention mechanism jointly learns single-domain and cross-domain preferences, mimicking human information integration. Evaluated on four e-commerce datasets, HAF-VT outperforms existing methods in capturing cross-domain user interests, bridging cognitive principles with computational models and highlighting the role of multimodal data in sequential decision-making.
View on arXiv@article{wu2025_2504.15085,
title={ Hierarchical Attention Fusion of Visual and Textual Representations for Cross-Domain Sequential Recommendation },
author={ Wangyu Wu and Zhenhong Chen and Siqi Song and Xianglin Qiua and Xiaowei Huang and Fei Ma and Jimin Xiao },
journal={arXiv preprint arXiv:2504.15085},
year={ 2025 }
}