Jul 2026· Journal of Organizational and End User Computing· 0 citations
TL;DR
A unified multimodal search framework that integrates generative AI-based captioning and image understanding for improved retrieval, enabling more accurate, context-aware search in applications such as e-commerce, multimedia, and large-scale retrieval.
Abstract
Visual search systems often rely on image-only embeddings, limiting semantic understanding—especially with visually similar but semantically distinct items. To overcome this, the authors propose a unified multimodal search framework that integrates generative AI-based captioning and image understanding for improved retrieval. Using Qwen2-VL-7B, the system generates rich captions from images, then fuses visual and textual embeddings via cross-attention. A re-ranking module refines the results. Evaluated on COCO Captions and Fashion-Gen, the model achieves BLEU scores of 0.78 and 0.75, CIDEr scores of 1.12 and 1.08, and retrieval mAP of 0.75 and 0.73. It also records NDCG@10 of 0.91 and 0.89, outperforming baselines like FineCaption, SuperCap, and MM-Transformer by up to 9%. These results validate the approach in bridging the semantic gap between images and text, enabling more accurate, context-aware search in applications such as e-commerce, multimedia, and large-scale retrieval.
A new model based on a Large Multimodal Model (LMM) that functions as a context-aware reasoner for CoCo-IR is proposed, which interprets the entire interaction history to generate Transformable Image Embeddings (TIE) that evolve across turns.
Shengcao Cao, T. Dabral, Z. Ding et al.· 0 citations
Multimodal retrieval and classification across different types of media, spanning text, images,video and audio, has traditionally relied on dual-encoder models that align visual and textual representations through contrastive learning. The March 2026 release of Gemini Embedding 2, Google's first natively multimodal embedding model to map text, images, video, audio, and documents into a single shared space, raises competition among multimodal retrieval systems. Simultaneously, frontier Large language models (LLMs) have also demonstrated strong visual understanding, raising the question of whether they can serve as effective zero-shot rankers. Our study provides the first direct comparison of native multimodal embeddings against LLM-based visual ranking on Flickr30k. We observe that GPT-4.1 and Claude Sonnet 4.6 perform on par with Gemini Embedding 2. Additionally, once embeddings are precomputed, multimodal embeddings are better suited for low-latency applications.
This paper introduces a Vision-Free CIR framework that addresses this challenge through two key techniques: Attribute-Augmented Hybrid Scoring, which compensates for lost visual details via explicit attribute matching, and LLM-Based Reranking, which verifies semantic consistency of top candidates.
Ryotaro Shimada, Yu-Chieh Lin, Yuji Nozawa et al.· 1 citation
Results demonstrate a 157% improvement in retrieval quality over a Naive-RAG baseline, with only 50 ms additional la tency, while Qwen2-VL-2B-Instruct achieved results comparable to cloud-based models in BERTScore, validate that open-source optimized SLMs, paired with advanced retrieval strategies, can provide competitive performance for document understanding without relying on cloud-based models.
[Objective] This study aims to improve textual similarity measurement for image retrieval while mitigating the anisotropy of sentence embeddings. [Methods] We propose an image-caption semantic encoder trained with a multi-positive contrastive loss. The conventional contrastive objective is extended to accommodate multiple positive samples, and image captioning is used to generate training data automatically. On this basis, we construct a caption-based image-to-image retrieval framework. [Results] Experiments show that the proposed model outperforms baseline methods on semantic textual similarity (STS) benchmarks and improves the agreement between retrieval results and human semantic judgments. [Limitations] Short captions cannot fully represent the complex semantics, ambiguity, and fine-grained details of an image. [Conclusion] The proposed Multi-Positive Example Contrastive Learning (MPC) model provides more discriminative sentence embeddings and improves semantic similarity measurement in image retrieval.
Danyang Cao, Li Cheng, Hongbo Zhou· Frontiers in Science and Eng...· 0 citations
Retrieval-Augmented Generation (RAG) has established itself as a compelling strategy for grounding large language model outputs in documentary evidence. However, production deployments continue to rely almost exclusively on homogeneous text corpora, even as enterprise repositories grow increasingly heterogeneous blending technical schematics, radiological images, annotated diagrams, and unstructured prose within the same archival system. This mismatch between system design and data reality motivates the present work. We propose a Multimodal RAG framework that unifies text and image retrieval through four tightly coupled components: a dual-stream embedding engine, a learned four-class AI query router, an adaptive confidence threshold, and a session-aware context store. Text is encoded with the allmpnet-base-v2 Sentence Transformer; images are embedded in the same 768-dimensional space via a domain-adapted CLIP ViT-L/14 model fine-tuned on approximately 120,000 technical and clinical text-image pairs. Concatenating 768-d vectors yields a 1,536-d composite query that drives a single approximate nearest-neighbor (ANN) search simultaneously across both modalities. A fine-tuned DistilBERT router assigns each query to one of four retrieval pathways text-only, image-only, hybrid, or conversational at 91.3% accuracy. Experiments were run on three enterprise corpora (engineering manuals, clinical case summaries, and legal paperwork) with the results being a mean F1@5 of 0.90, an increase of 22% over a dense text-only baseline, and a reduction of 49% in the number of hallucinations. The median first-token latency is 1.34s, which meets the interactive-use target deployment-contexts. These results show that it is possible to implement modality-aware retrieval in a simple and realistic setting with real-world organizational constraints and that the results are reproducible.
E.Vijayakumar, Ganesh A· 2026 4th International Confe...· 0 citations