paper-with-me

Papers

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

2025-11-26 · Xiaoxing You, Qiang Huang, Lingyu Li, Chi Zhang, Xiaopeng Liu, Min Zhang, Jun Yu arxiv

News image captioning aims to produce journalistically informative descriptions by combining visual content with contextual cues from associated articles. Despite recent advances, existing methods struggle with three key challenges: (1) incomplete information coverage, (2) weak cross-modal alignment, and (3) suboptimal visual-entity grounding. To address these issues, we introduce MERGE, the first Multimodal Entity-aware Retrieval-augmented GEneration framework for news image captioning. MERGE constructs an entity-centric multimodal knowledge base (EMKB) that integrates textual, visual, and structured knowledge, enabling enriched background retrieval. It improves cross-modal alignment through a multistage hypothesis-caption strategy and enhances visual-entity matching via dynamic retrieval guided by image content. Extensive experiments on GoodNews and NYTimes800k show that MERGE significantly outperforms state-of-the-art baselines, with CIDEr gains of +6.84 and +1.16 in caption quality, and F1-score improvements of +4.14 and +2.64 in named entity recognition. Notably, MERGE also generalizes well to the unseen Visual News dataset, achieving +20.17 in CIDEr and +6.22 in F1-score, demonstrating strong robustness and domain adaptability.

📄 PDF Abstract BibTeX arXiv:2511.21002

Code (0)

등록된 구현이 없습니다.

Tasks

Image Captioning

Similar Papers 제목 키워드 기반

AMELI: Enhancing Multimodal Entity Linking with Fine-Grained Attributes

2023-05-24 · Barry Menglong Yao, Yu Chen, Qifan Wang, Sijia Wang 외

We propose attribute-aware multimodal entity linking, where the input is a mention described with a text and image, and the goal is to predict the corresponding target entity from a multimodal knowledge base (KB) where e…

AttributeEntity Linking

E2E-GMNER: End-to-End Generative Grounded Multimodal Named Entity Recognition

2026-04-19 · Meng Zhang, Jinzhong Ning, Xiaolong Wu, Hongfei Lin 외 arxiv

Grounded Multimodal Named Entity Recognition (GMNER) aims to jointly identify named entity mentions in text, predict their semantic types, and ground each entity to a corresponding visual region in an associated image. E…

Grounded Multimodal Named Entity RecognitionVisual Grounding

Visual Text Matters: Improving Text-KVQA with Visual Text Entity Knowledge-aware Large Multimodal Assistant

2024-10-24 · Abhirama Subramanyam Penamakuri, Anand Mishra

We revisit knowledge-aware text-based visual question answering, also known as Text-KVQA, in the light of modern advancements in large multimodal models (LMMs), and make the following contributions: (i) We propose VisTEL…

Entity LinkingQuestion AnsweringVisual Question Answering

Empower Sequence Labeling with Task-Aware Neural Language Model

2017-09-13 · Liyuan Liu, Jingbo Shang, Frank F. Xu, Xiang Ren 외

Linguistic sequence labeling is a general modeling approach that encompasses a variety of problems, such as part-of-speech tagging and named entity recognition. Recent advances in neural networks (NNs) make it possible t…

GPULanguage ModelingLanguage Modellingnamed-entity-recognition+6

Knowledge Guided Entity-aware Video Captioning and A Basketball Benchmark

2024-01-25 · Zeyu Xi, Ge Shi, Xuefen Li, Junchi Yan 외

Despite the recent emergence of video captioning models, how to generate the text description with specific entity names and fine-grained actions is far from being solved, which however has great applications such as bas…

DecoderVideo Captioning