EAMA : Entity-Aware Multimodal Alignment Based Approach for News Image Captioning

• URL: http://arxiv.org/abs/2402.19404v4
• Date: Mon, 6 May 2024 14:41:56 GMT
• Title: EAMA : Entity-Aware Multimodal Alignment Based Approach for News Image Captioning
• Authors: Junzhe Zhang, Huixuan Zhang, Xunjian Yin, Xiaojun Wan,
• Abstract summary: News image captioning requires model to generate an informative caption rich in entities, with the news image and the associated news article. Current Multimodal Large Language Models (MLLMs) still bear limitations in handling entity information on news image captioning task. Our approach achieves better results than all previous models in CIDEr score on GoodNews dataset (72.33 -> 88.39) and NYTimes800k dataset (70.83 -> 85.61)
• Score: 55.033327333250455
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: News image captioning requires model to generate an informative caption rich in entities, with the news image and the associated news article. Though Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities in addressing various vision-language tasks, our research finds that current MLLMs still bear limitations in handling entity information on news image captioning task. Besides, while MLLMs have the ability to process long inputs, generating high-quality news image captions still requires a trade-off between sufficiency and conciseness of textual input information. To explore the potential of MLLMs and address problems we discovered, we propose : an Entity-Aware Multimodal Alignment based approach for news image captioning. Our approach first aligns the MLLM through Balance Training Strategy with two extra alignment tasks: Entity-Aware Sentence Selection task and Entity Selection task, together with News Image Captioning task, to enhance its capability in handling multimodal entity information. The aligned MLLM will utilizes the additional entity-related information it explicitly extracts to supplement its textual input while generating news image captions. Our approach achieves better results than all previous models in CIDEr score on GoodNews dataset (72.33 -> 88.39) and NYTimes800k dataset (70.83 -> 85.61).

Related papers

• FTII-Bench: A Comprehensive Multimodal Benchmark for Flow Text with Image Insertion [7.23608073306791]
  Flow Text with Image Insertion task requires LVLMs to simultaneously possess outstanding abilities in image comprehension, instruction understanding, and long-text interpretation. We introduce the Flow Text with Image Insertion Benchmark (FTII-Bench), which includes 318 high-quality Chinese image-text news articles and 307 high-quality English image-text news articles, covering 10 different news domains. We evaluate 9 open-source and 2 closed-source LVLMs as well as 2 CLIP-based models.
  arXiv  Detail & Related papers  (2024-10-16T13:38:31Z)
• AdaptVision: Dynamic Input Scaling in MLLMs for Versatile Scene Understanding [96.01726275876548]
  We present AdaptVision, a multimodal large language model specifically designed to dynamically process input images at varying resolutions. We devise a dynamic image partitioning module that adjusts the number of visual tokens according to the size and aspect ratio of images. Our model is capable of processing images with resolutions up to $1008times 1008$.
  arXiv  Detail & Related papers  (2024-08-30T03:16:49Z)
• Semantic Alignment for Multimodal Large Language Models [72.10272479476161]
  We introduce Semantic Alignment for Multi-modal large language models (SAM) By involving the bidirectional semantic guidance between different images in the visual-token extraction process, SAM aims to enhance the preservation of linking information for coherent analysis. By involving the bidirectional semantic guidance between different images in the visual-token extraction process, SAM aims to enhance the preservation of linking information for coherent analysis.
  arXiv  Detail & Related papers  (2024-08-23T06:48:46Z)
• Rethinking Visual Prompting for Multimodal Large Language Models with External Knowledge [76.45868419402265]
  multimodal large language models (MLLMs) have made significant strides by training on vast high-quality image-text datasets. However, the inherent difficulty in explicitly conveying fine-grained or spatially dense information in text, such as masks, poses a challenge for MLLMs. This paper proposes a new visual prompt approach to integrate fine-grained external knowledge, gleaned from specialized vision models, into MLLMs.
  arXiv  Detail & Related papers  (2024-07-05T17:43:30Z)
• ANCHOR: LLM-driven News Subject Conditioning for Text-to-Image Synthesis [6.066100464517522]
  We introduce the Abstractive News Captions with High-level cOntext Representation dataset, containing 70K+ samples sourced from 5 different news media organizations. Our proposed method Subject-Aware Finetuning (SAFE), selects and enhances the representation of key subjects in synthesized images by leveraging LLM-generated subject weights. It also adapts to the domain distribution of news images and captions through custom Domain Fine-tuning, outperforming current T2I baselines on ANCHOR.
  arXiv  Detail & Related papers  (2024-04-15T21:19:10Z)
• MLLMs-Augmented Visual-Language Representation Learning [70.5293060238008]
  We demonstrate that Multi-modal Large Language Models (MLLMs) can enhance visual-language representation learning. Our approach is simple, utilizing MLLMs to extend multiple diverse captions for each image. We propose "text shearing" to maintain the quality and availability of extended captions.
  arXiv  Detail & Related papers  (2023-11-30T18:05:52Z)
• Text as Images: Can Multimodal Large Language Models Follow Printed Instructions in Pixels? [158.96530466189986]
  multimodal large language models (MLLMs) have shown promising instruction following capabilities on vision-language tasks. We investigate how well multimodal models can understand textual instructions provided in pixels, despite not being explicitly trained on such data during pretraining or fine-tuning. We train v-MLLM, a generalizable model that is capable to conduct robust instruction following in both text-modality and visual-modality instructions.
  arXiv  Detail & Related papers  (2023-11-29T14:08:53Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.