Towards Training-Free Long-Form Image Captioning: A Divide-and-Conquer Strategy
Linkai Zhu1, Chaofan Li1, Lu Yang1, Changpu Meng2, Lu Liu3,*
1 School of Management Science and Information Engineering, Hebei University of Economics and Business, Shijiazhuang, China
2 School of Computing and Information Technology, University of Wollongong, Wollongong, NSW, Australia
3 School of Cyber Science and Technology, Shandong University, Qingdao, China
* Corresponding Author: Lu Liu. Email: 
Computers, Materials & Continua https://doi.org/10.32604/cmc.2026.087313
Received 14 June 2026; Accepted 28 August 2026; Published online 20 September 2026
Abstract
Long-form image captions are valuable for image–text retrieval, visual question answering, and generative applications, but multimodal large language models (MLLMs) still face a persistent trade-off between fine-grained semantic coverage and visual faithfulness. To address this problem, we propose a training-free divide-and-conquer framework for reliable long-form image captioning. Inspired by Feature Integration Theory, the framework decomposes an image into four object-aware spatial regions and one key semantic region, samples multiple regional captions, and progressively integrates verified evidence through same-region semantic fusion, cross-region semantic fusion, and key-semantic-region-guided global refinement. To reduce hallucination during aggregation, unreliable regional and cross-region candidates are removed by image–text consistency verification, and the final caption is further filtered at the semantic-unit level by combining Contrastive Language-Image Pre-training (CLIP) alignment, Bootstrapping Language-Image Pre-training with frozen image encoders and large language models (BLIP-2) generation consistency, and hyperspherical feature similarity. Experiments on the Detailed Image Description Benchmark (DID-Bench) across open-source Large Language and Vision Assistant (LLaVA) models and proprietary MLLMs show that the proposed framework improves caption quality, semantic coverage, visual consistency, and hallucination suppression without retraining or fine-tuning. In particular, it achieves fine-grained semantic-coverage scores of 58.88 and 64.48 on LLaVA-1.5-7B and LLaVA-1.6-7B, respectively. On the 400-image ImageInWords subset (IIW-400), the framework obtains the best Bilingual Evaluation Understudy (BLEU) and Semantic Propositional Image Caption Evaluation (SPICE) scores among the evaluated methods, although other automatic metrics remain model- and metric-dependent. A human evaluation on 50 randomly selected IIW-400 images further shows the highest factual-correctness and detail-coverage scores, while the Image Textualization (IT) baseline retains the highest readability score. These results indicate that the proposed framework can improve visually grounded long-form captioning in the evaluated natural-image settings, with remaining limitations in inference efficiency and domain generalization.
Keywords
Image captioning; multimodal large language models; semantic fusion; hallucination mitigation; training-free framework
Open Access
Login
Register
Submit a Paper
Propose a Special lssue
Download PDF
Downloads
Citation Tools
