gsoykan / comics_text_plus
Official repository of the paper: "A Comprehensive Gold Standard and Benchmark for Comics Text Detection and Recognition"
☆26Updated last year
Alternatives and similar repositories for comics_text_plus:
Users that are interested in comics_text_plus are comparing it to the libraries listed below
- COO: Comic onomatopoeia dataset (ECCV 2022)☆75Updated this week
- A simple tool to estimate the reading order of comic panels☆15Updated 2 years ago
- An implementation of Tiling and Corruption (TACo) Augmentations for OCR/HTR☆15Updated 3 years ago
- Official repository accompaying the ICDAR 2023 paper☆11Updated last year
- ☆12Updated 9 months ago
- Cross-lingual learning in scene text recognition (ICASSP2024)☆15Updated 4 months ago
- The largest VQA dataset for Vietnamese. Related to the text content in the image.☆15Updated this week
- Code for AAAI 2023 Paper : “Alignment-Enriched Tuning for Patch-Level Pre-trained Document Image Models”☆17Updated 2 years ago
- This repository contains source codes for SoftCTC. Original paper can be found here: https://arxiv.org/abs/2212.02135☆19Updated last year
- ☆38Updated last year
- CTE: Contextualized Table Extraction Dataset☆17Updated last year
- A dashboard for exploring timm learning rate schedulers☆19Updated 2 months ago
- ☆18Updated last year
- WikiTableSet: A largest publicly available image-based table recognition dataset in three languages built from Wikipedia☆27Updated last year
- In-Context Alignment: Chat with Vanilla Language Models Before Fine-Tuning☆33Updated last year
- Implementation of the DocLLM paper for Llama models.☆12Updated 2 months ago
- ☆42Updated 2 years ago
- Description and applications of OpenAI's paper about DALL-E (2021) and implementation of other (CLIP-guided) zero-shot text-to-image gene…☆30Updated 2 years ago
- Text-DIAE: A Self-Supervised Degradation Invariant Autoencoders for Text Recognition and Document Enhancement - AAAI 2023☆23Updated last year
- Load any clip model with a standardized interface☆21Updated 9 months ago
- OCR-VQGAN, a discrete image encoder (tokenizer and detokenizer) for figure images in Paper2Fig100k dataset. Implementation of OCR Percept…☆76Updated 2 years ago
- Tools for content datamining and NLP at scale☆42Updated 8 months ago
- High-Performance Transformers for Table Structure Recognition Need Early Convolutions☆42Updated 10 months ago
- Index of URLs to pdf files all over the internet and scripts☆21Updated last year
- Pixel Parsing. A reproduction of OCR-free end-to-end document understanding models with open data☆21Updated 6 months ago
- Seed Machine Translation Data☆30Updated 3 months ago
- [COLM 2024] Early Weight Averaging meets High Learning Rates for LLM Pre-training☆14Updated 4 months ago