Knowledge Completes the Vision: A Multimodal Entity-aware Retrieval-Augmented Generation Framework for News Image Captioning

Documenti analoghi

• Cut to the Chase: Training-free Multimodal Summarization via Chain-of-Events
  di: You, Xiaoxing, et al.
  Pubblicazione: (2026)
• MG$^2$-RAG: Multi-Granularity Graph for Multimodal Retrieval-Augmented Generation
  di: Dai, Sijun, et al.
  Pubblicazione: (2026)
• EAMA : Entity-Aware Multimodal Alignment Based Approach for News Image Captioning
  di: Zhang, Junzhe, et al.
  Pubblicazione: (2024)
• Knowledge Guided Entity-aware Video Captioning and A Basketball Benchmark
  di: Xi, Zeyu, et al.
  Pubblicazione: (2024)
• Retrieval-Augmented Egocentric Video Captioning
  di: Xu, Jilan, et al.
  Pubblicazione: (2024)