mlsanityData to 14 Oct 2026

Cognitive-Inspired Hierarchical Attention Fusion With Visual and Textual for Cross-Domain Sequential Recommendation

arXiv 2504.15085 ↗First posted 21 Apr 2025cs.CVcited by 2

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 44 of its 73 references that are in the map. First posted on arXiv 21 Apr 2025.

Builds on

44 of 73 references.

References · 44

  1. 2017Attention Is All You Needcited by 60,361
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  4. 2014Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modelingcited by 2,367
  5. 2018Self-Attentive Sequential Recommendationcited by 1,184
  6. 2015Session-based Recommendations with Recurrent Neural Networkscited by 695
  7. 2017Deep Interest Network for Click-Through Rate Predictioncited by 544
  8. 2018Personalized Top-N Sequential Recommendation via Convolutional Sequence Embeddingcited by 476
  9. 2018Deep Interest Evolution Network for Click-Through Rate Predictioncited by 338
  10. 2018Session-based Recommendation with Graph Neural Networkscited by 312
  11. 2024TFB: Towards Comprehensive and Fair Benchmarking of Time Series Forecasting Methodscited by 249
  12. 2017Neural Attentive Session-based Recommendationcited by 237
32 more
  1. 2016Fusing Similarity Models with Markov Chains for Sparse Sequential Recommendationcited by 152
  2. 2022Learning to Generate Text-grounded Mask for Open-world Semantic Segmentation from Only Image-Text Pairscited by 130
  3. 2019Sequential Recommender Systems: Challenges, Progress and Prospectscited by 115
  4. 2024DUET: Dual Clustering Enhanced Multivariate Time Series Forecastingcited by 107
  5. 2021Sequential Recommendation with Graph Neural Networkscited by 89
  6. 2018CoNet: Collaborative Cross Networks for Cross-Domain Recommendationcited by 81
  7. 2021Contrastive Learning for Cold-Start Recommendationcited by 79
  8. 2017Translation-based Recommendationcited by 71
  9. 2022Towards Visual-Prompt Temporal Answering Grounding in Medical Instructional Videocited by 43
  10. 2024Core Knowledge Deficits in Multi-Modal Language Modelscited by 38
  11. 2021DA-GCN: A Domain-aware Attentive Graph Convolution Network for Shared-account Cross-domain Sequential Recommendationcited by 34
  12. 2021More but Correct: Generating Diversified and Entity-revised Medical Responsecited by 31
  13. 2023Contrastive Cross-Domain Sequential Recommendationcited by 31
  14. 2020MiNet: Mixed Interest Network for Cross-Domain Click-Through Rate Predictioncited by 30
  15. 2024EasyTime: Time Series Forecasting Made Easycited by 30
  16. 2023Diverse Cotraining Makes Strong Semi-Supervised Segmentorcited by 26
  17. 2020Mixed Information Flow for Cross-domain Sequential Recommendationscited by 22
  18. 2019Parallel Split-Join Networks for Shared-account Cross-domain Sequential Recommendationscited by 21
  19. 2023Triple Sequence Learning for Cross-domain Recommendationcited by 19
  20. 2025MAGIC-VQA: Multimodal And Grounded Inference with Commonsense Knowledge for Visual Question Answeringcited by 19
  21. 2024Image Fusion for Cross-Domain Sequential Recommendationcited by 17
  22. 2021RecGURU: Adversarial Learning of Generalized User Representations for Cross-Domain Recommendationcited by 16
  23. 2024DiffSSC: Semantic LiDAR Scan Completion using Denoising Diffusion Probabilistic Modelscited by 16
  24. 2024ICH-SCNet: Intracerebral Hemorrhage Segmentation and Prognosis Classification Network Using CLIP-guided SAM mechanismcited by 16
  25. 2024Prompt Categories Cluster for Weakly Supervised Semantic Segmentationcited by 16
  26. 2024Event-guided Low-light Video Semantic Segmentationcited by 14
  27. 2024CrackNex: a Few-shot Low-light Crack Segmentation Model Based on Retinex Theory for UAV Inspectionscited by 12
  28. 2024SLCF-Net: Sequential LiDAR-Camera Fusion for Semantic Scene Completion using a 3D Recurrent U-Netcited by 12
  29. 2022Towards Better Chinese-centric Neural Machine Translation for Low-resource Languagescited by 11
  30. 2024Multimodal Commonsense Knowledge Distillation for Visual Question Answeringcited by 11
  31. 2025Spiking Point Transformer for Point Cloud Classificationcited by 7
  32. 2023Dual-interest Factorization-heads Attention for Sequential Recommendationcited by 6

Built on by

Cited by year

Citing papers per year: 2025: 2.

2 papers.

  1. 2025Tag-Enriched Multi-Attention with Large Language Models for Cross-Domain Sequential Recommendationcited by 0
  2. 2025Context-Aware Pseudo-Label Scoring for Zero-Shot Video Summarizationcited by 0