{
  "annotation_id": "14332506-9ba2-47f3-a9f5-8f1bcd041a1e",
  "date_created": "2026-02-17T05:53:20.064000Z",
  "date_modified": "2026-02-17T05:53:20.064000Z",
  "file_hash": "2710e3de7f02ddf94bca088298721ff547bb729c57fd51c3f75fbf12373f1894",
  "private": false,
  "record": {
    "abstract": "Real-world License Plate Recognition (LPR) faces significant challenges from severe degradations such as motion blur, low resolution, and complex illumination. The prevailing \"restoration-then-recognition\" two-stage paradigm suffers from a fundamental flaw: the pixel-level optimization objectives of image restoration models are misaligned with the semantic goals of character recognition, leading to artifact interference and error accumulation. While Vision-Language Models (VLMs) have demonstrated powerful general capabilities, they lack explicit structural modeling for license plate character sequences (e.g., fixed length, specific order). To address this, we propose an end-to-end structure-aware multimodal reasoning framework based on Qwen3-VL. The core innovation lies in the Character-Aware Multimodal Reasoning Module (CMRM), which introduces a set of learnable Character Slot Queries. Through a cross-attention mechanism, these queries actively retrieve fine-grained evidence corresponding to character positions from visual features. Subsequently, we inject these character-aware representations back into the visual tokens via residual modulation, enabling the language model to perform autoregressive generation based on explicit structural priors. Furthermore, combined with the LoRA parameter-efficient fine-tuning strategy, the model achieves domain adaptation while retaining the generalization capabilities of the large model. Extensive experiments on both synthetic and real-world severely degraded datasets demonstrate that our method significantly outperforms existing restoration-recognition combinations and general VLMs, validating the superiority of incorporating structured reasoning into large models for low-quality text recognition tasks.",
    "arxiv_id": "2601.09116",
    "authors": [
      "Haoyan Gong",
      "Hongbin Liu"
    ],
    "categories": [
      "cs.CV",
      "cs.AI"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "title": "LP-LLM: End-to-End Real-World Degraded License Plate Text Recognition via Large Multimodal Models",
    "url": "https://arxiv.org/abs/2601.09116",
    "version": "v1"
  },
  "schema_id": "dorsal/arxiv",
  "source": {
    "execution_id": "714ce33c-f05b-46ab-913b-48d1f7c328ea",
    "id": "arXiv Dataset",
    "type": "Model",
    "variant": "snapshot-2026-01-17",
    "version": "0.1.0"
  },
  "user_id": 1000002
}