All Stories

  1. Prior Knowledge Integration via LLM Encoding and Pseudo Event Regulation for Video Moment Retrieval
  2. Learning to Correction: Explainable Feedback Generation for Visual Commonsense Reasoning Distractor
  3. Deconfounded Emotion Guidance Sticker Selection with Causal Inference
  4. MaterialSeg3D: Segmenting Dense Materials from 2D Priors for 3D Assets
  5. Generative Active Learning for Image Synthesis Personalization
  6. A Picture Is Worth a Graph: A Blueprint Debate Paradigm for Multimodal Reasoning
  7. Effective Illicit Account Detection on Large Cryptocurrency MultiGraphs
  8. Efficient and Robust Regularized Federated Recommendation
  9. Multi-agent Attacks for Black-box Social Recommendations
  10. A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Models
  11. Fast Graph Condensation with Structure-based Neural Tangent Kernel
  12. FashionReGen: LLM-Empowered Fashion Report Generation
  13. Large Language Models for Graph Learning
  14. Deconfounded Visual Question Generation with Causal Inference
  15. LinRec: Linear Attention Mechanism for Long-term Sequential Recommender Systems
  16. Fairly Adaptive Negative Sampling for Recommendations
  17. Visual Paraphrase Generation with Key Information Retained
  18. Cycle Encoding of a StyleGAN Encoder for Improved Reconstruction and Editability
  19. Knowledge-enhanced Black-box Attacks for Recommendations
  20. A Label Extension Schema for Improved Text Emotion Classification
  21. Multi-branch Semantic Learning Network for Text-to-Image Synthesis
  22. Adversarial Learning with Mask Reconstruction for Text-Guided Image Inpainting
  23. Scene Graph with 3D Information for Change Captioning
  24. Hierarchical Visual-aware Minimax Ranking Based on Co-purchase Data for Personalized Recommendation
  25. Learning Shared Semantic Space with Correlation Alignment for Cross-Modal Event Retrieval
  26. Cross-domain Beauty Item Retrieval via Unsupervised Embedding Learning
  27. Deep social collaborative filtering
  28. EAN
  29. Deep Semantic Space with Intra-class Low-rank Constraint for Cross-modal Retrieval
  30. Learning from Multi-annotator Data