Latest Research in Computer Vision and Pattern Recognition
27 research papers · 2026 median publication year
Top Research Topics in Computer Vision and Pattern Recognition
- Computer Vision and Pattern Recognition — 13 papers
- Handwritten Text Recognition Techniques — 6 papers
- Computation and Language — 5 papers
- Artificial Intelligence — 2 papers
- Machine Learning — 1 papers
Highest-Cited Papers
- JieZi: A Large-Scale Expert-Audited Dataset and Benchmark for Ancient Chinese Character Exegesis
- TongGuOCR: A Layout-Aware and Token-Augmented OCR MLLM for Chinese Historical Documents
- LLM-Driven AutoML for Cross-Lingual Handwritten OCR: Closed-Loop Neural Architecture Search with GPT-5, GPT-4o, and Claude Sonnet 4
- Robust recognition of Tamil inscription letters using a hybrid model combining recurrent neural networks, graph neural networks, and attention mechanisms
- CC-OCR V2: Fine-Grained Attribution of LMM Failures in Real-World Visual Document Understanding
- Stoicheia: Character-Level Masked Diffusion for Ancient Greek Textual Restoration, Parsing, and Metrical Scansion
- Judge a Book by its Cover: Investigating Multi-Modal LLMs for Multi-Page Handwritten Document Transcription
- HunyuanOCR-1.5: Making Lightweight OCR VLMs Faster and Better
- DTRNet: Dual Text-Radical Decoding for Handwritten Chinese Text Recognition with Faked Character Detection
- Mapping Armenian Paris: Extracting and Geocoding Commercial Advertisements from the 20th-Century Diaspora Press
- A machine-readable catalogue of the Tsiolkovsky papers (fond 555, Archive of the Russian Academy of Sciences), and a way to measure how well its handwriting can be read
- BanglaWild: An In-the-Wild Bengali Scene Text Recognition Benchmark for OCR and Vision-Language Models
- Can You Trust the Confidence? ConfBench for Vision-Language Models on Document Extraction
- Large language models for OCR in cultural heritage: a comparative study on Slovene Folkloristic texts
- MinerU-Popo: Universal Post-Processing Model for Structured Document Parsing
- Logographic Character Visual Pretraining via Semantic-based Contrastive Learning
- AI-Assisted Digitalization of Heterogeneous Government Archives in Low-Resource Countries: A Vision Language Model Case Study from Chad
- AI-Assisted Digitalization of Heterogeneous Government Archives in Low-Resource Countries: A Vision Language Model Case Study from Chad
- When Low CER is Not Enough: An Analysis of Hallucinations in Vision-Language OCR Systems on Historical Uruguayan Documents
- A document is worth a structured record: Principled inductive bias design for document recognition