CIAN: Multi-Stage Framework for Event-Enriched Image Captioning via Retrieval-Augmented Generation
On the map: Retrieval-augmented generation → Multimodal RAG
Abstract (arXiv)
Event-enriched image captioning describes not only visible content but also the broader context of events, including timing, location, and participants, capabilities missing in most pixel-bound models. We propose the Contextual Image-Article Narrator (CIAN), a multi-stage framework that enriches captions with external narratives. CIAN retrieves relevant articles using SigLIP, summarizes them to guide a Narrative Generation stage with a LoRA-fine-tuned Qwen model, and applies N-Gram-based Refinement for fluency and coherence. On the OpenEvents-V1 benchmark, CIAN achieves high retrieval performance (mAP 0.979) and improves caption quality, increasing CIDEr from 0.030 to 0.094. These results highlight the effectiveness of retrieval-augmented reasoning combined with linguistic refinement for generating context-aware, human-like captions.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Multimodal RAG, one of 15 directions in Retrieval-augmented generation. Builds on 20 of its 28 references that are in the map. First posted on arXiv 16 Jun 2026.
Builds on
20 of 28 references.
References · 20
- 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
- 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
- 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
- 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
- 2022BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generationcited by 4,310
- 2024Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolutioncited by 4,151
- 2021Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervisioncited by 3,848
- 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
- 2023Sigmoid Loss for Language Image Pre-Trainingcited by 3,048
- 2014Sequence to Sequence Learning with Neural Networkscited by 2,974
- 2021CLIPScore: A Reference-free Evaluation Metric for Image Captioningcited by 2,388
- 2014CIDEr: Consensus-based Image Description Evaluationcited by 2,027
8 more
- 2024LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Modelscited by 1,442
- 2023A Survey on Multimodal Large Language Modelscited by 898
- 2018Stacked Cross Attention for Image-Text Matchingcited by 414
- 2018A Comprehensive Survey of Deep Learning for Image Captioningcited by 213
- 2021From Show to Tell: A Survey on Deep Learning-based Image Captioningcited by 137
- 2025Image Captioning Evaluation in the Age of Multimodal LLMs: Challenges and Future Perspectivescited by 17
- 2025OpenEvents V1: Large-Scale Benchmark Dataset for Multimodal Event Groundingcited by 8
- 2025Event-Enriched Image Analysis Grand Challenge at ACM Multimedia 2025cited by 3
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2025ReCap: Event-Aware Image Captioning with Article Retrieval and Semantic Gaussian Normalization
- 2026Hierarchical Multi-Modal Retrieval for Knowledge-Grounded News Image Captioning
- 2024Towards Retrieval-Augmented Architectures for Image Captioning
- 2025Knowledge Completes the Vision: A Multimodal Entity-aware Retrieval-Augmented Generation Framework for News Image Captioning
- 2025Leveraging Lightweight Entity Extraction for Scalable Event-Based Image Retrieval
- 2023Retrieval-augmented Image Captioning
- 2022CLIP-Event: Connecting Text and Images with Event Structures
- 2022Retrieval-Augmented Transformer for Image Captioning