Skip to content

@SCUT-DLVCLab SCUT-DLVCLab

Change the repository type filter

All

    Repositories list

    21 repositories

    • SigBench

      Public
      GNU General Public License v3.0
      •0•0•0•0•Updated Jun 1, 2025Jun 1, 2025

    • OCR-Reasoning

      Public
      [arXiv: 2505.17163] OCR-Reasoning Benchmark: Unveiling the True Capabilities of MLLMs in Complex Text-Rich Image Reasoning
      Python
      •
      Apache License 2.0
      •2•37•1•0•Updated May 27, 2025May 27, 2025

    • PAVENet

      Public
      [IEEE TPAMI 2025] Official repository of "Privacy-Preserving Biometric Verification With Handwritten Random Digit String".
      Python
      •
      GNU General Public License v3.0
      •0•6•0•0•Updated May 25, 2025May 25, 2025

    • LongHisDoc

      Public
      A Comprehensive Benchmark for Chinese Long Historical Document Understanding
      Python
      •0•1•0•0•Updated May 23, 2025May 23, 2025

    • AutoHDR

      Public
      [ACL 2025 main] The official GitHub page of "Reviving Cultural Heritage: A Novel Approach for Comprehensive Historical Document Restoration"
      0•5•0•0•Updated May 20, 2025May 20, 2025

    • DOLPHIN

      Public
      [IEEE TIFS 2024] Official repository of "Online Writer Retrieval with Chinese Handwritten Phrases: A Synergistic Temporal-Frequency Representation Learning Approach".
      Python
      •
      GNU General Public License v3.0
      •0•9•0•0•Updated May 17, 2025May 17, 2025

    • AutoScaler

      Public
      The official GitHub page of "AutoScaler: Self Scale Alignment for Handwritten Mathematical Expression Recognition"
      Python
      •0•3•0•0•Updated May 15, 2025May 15, 2025

    • MegaHan97K

      Public
      [PR 2025] The official GitHub page of "MegaHan97K: A Large-Scale Dataset for Mega-Category Chinese Character Recognition with over 97K Categories"
      Python
      •0•20•0•0•Updated May 12, 2025May 12, 2025

    • ACP-RAG

      Public
      [NAACL 2025] Large-Scale Corpus Construction and Retrieval-Augmented Generation for Ancient Chinese Poetry: New Method and Data Insights (ACP-Corpus; ACP-QA; ACP-RAG)
      Python
      •0•3•0•0•Updated May 6, 2025May 6, 2025

    • MCS-Bench

      Public
      Python
      •0•2•0•0•Updated May 6, 2025May 6, 2025

    • C3bench

      Public
      C3 benchmark
      0•2•1•0•Updated Mar 30, 2025Mar 30, 2025

    • HisDoc1B

      Public
      1•11•1•0•Updated Mar 2, 2025Mar 2, 2025

    • Document-AI-Recommendations

      Public
      Algorithms, papers, datasets, performance comparisons for Document AI. Continuously updating.
      document-understandingtable-structure-recognitionkey-information-extractiondocument-aivisual-information-extraction
      7•193•0•0•Updated Mar 1, 2025Mar 1, 2025

    • DCOH-120K

      Public
      1•3•0•0•Updated Feb 20, 2025Feb 20, 2025

    • RFUND

      Public
      [MM'2024] Official release of RFUND introduced in the MM'2024 paper "PEneo: Unifying Line Extraction, Line Grouping, and Entity Linking for End-to-end Document Pair Extraction"
      ocrdocument-understandingkey-information-extractiondocument-aivisual-information-extraction
      0•19•0•0•Updated Dec 4, 2024Dec 4, 2024

    • TongGu-LLM

      Public
      [EMNLP 2024] TongGu, a classical Chinese language model.
      1•38•5•0•Updated Sep 28, 2024Sep 28, 2024

    • WenMind

      Public
      WenMind benchmark.
      Python
      •1•6•0•0•Updated Sep 26, 2024Sep 26, 2024

    • .github

      Public
      0•0•0•0•Updated Jun 4, 2024Jun 4, 2024

    • SCUT-EnsExam

      Public
      SCUT-EnsExam is a real-world handwritten text erasure dataset for examination paper scenarios, which consists of 545 examination paper images. The dataset is randomly divided into training set and test set of 430 and 115 images, respectively.
      0•11•0•0•Updated Dec 5, 2023Dec 5, 2023

    • GPT-4V_OCR

      Public
      Evaluation of the Optical Character Recognition (OCR) capabilities of GPT-4V(ision)
      Python
      •4•124•0•0•Updated Nov 13, 2023Nov 13, 2023

    • Mnist-99.7-Accuracy-with-Pytorch

      Public
      A CNN model builds with Pytorch and reaches 99.7% accuracy
      pyqt5pytorchguimnist
      Python
      •2•4•0•0•Updated May 1, 2021May 1, 2021