Bridging Coarse and Fine Recognition: A Hybrid Approach for Open-Ended Multi-Granularity Object Recognition in Interactive Educational Games

TL;DR

HyMOR is a hybrid framework combining large language models and CLIP to improve multi-granularity object recognition for educational games, enabling accurate perception across semantic levels.

Contribution

The paper introduces HyMOR, a novel hybrid approach integrating MLLMs and CLIP models for open-ended, multi-granularity object recognition in educational and interactive scenarios.

Findings

HyMOR narrows the fine-grained recognition gap to 0.2%.

HyMOR improves general object recognition by 2.5%.

HyMOR achieves a 23.2% overall improvement in semantic similarity.

Abstract

Recent advances in Multimodal Large Language Models (MLLMs) have enabled open-ended object recognition, yet they struggle with fine-grained tasks. In contrast, CLIP-style models excel at fine-grained recognition but lack broad coverage of general object categories. To bridge this gap, we propose \textbf{HyMOR}, a \textbf{Hy}brid \textbf{M}ulti-granularity open-ended \textbf{O}bject \textbf{R}ecognition framework that integrates an MLLM with a CLIP model. In HyMOR, the MLLM performs open-ended and coarse-grained object recognition, while the CLIP model specializes in fine-grained identification of domain-specific objects such as animals and plants. This hybrid design enables accurate object understanding across multiple semantic granularities, serving as a robust perceptual foundation for downstream multi-modal content generation and interactive gameplay. To support evaluation in content-rich and educational scenarios, we introduce TBO (TextBook Objects), a dataset containing 20,942 images annotated with 8,816 object categories extracted from textbooks. Extensive experiments demonstrate that HyMOR narrows the fine-grained recognition gap with CLIP to 0.2\% while improving general object recognition by 2.5\% over a baseline MLLM, measured by average Sentence-BERT (SBert) similarity. Overall, HyMOR achieves a 23.2\% improvement in average SBert across all evaluated datasets, highlighting its effectiveness in enabling accurate perception for multi-modal game content generation and interactive learning applications.