huizhang0110 / catvision
A multimodal large-scale model, which performs close to the closed-source Qwen-VL-PLUS on many datasets and significantly surpasses the performance of the open-source model Qwen-VL-7B-Chat.
☆14Updated 7 months ago
Related projects: ⓘ
- Chinese CLIP models with SOTA performance.☆44Updated last year
- ☆10Updated this week
- ☆17Updated this week
- A Dead Simple and Modularized Multi-Modal Training and Finetune Framework. Compatible to any LLaVA/Flamingo/QwenVL/MiniGemini etc series …☆17Updated 4 months ago
- WikiTableSet: A largest publicly available image-based table recognition dataset in three languages built from Wikipedia☆23Updated last year
- paddle code convert toolkit☆22Updated last year
- ☆13Updated this week
- ☆13Updated last year
- BTS: A Bi-lingual Benchmark for Text Segmentation in the Wild☆24Updated 5 months ago
- A simple middleware to improving GPU utilization then speedup online inference.☆19Updated 3 years ago
- ☆18Updated 3 years ago
- The official repo for “TextCoT: Zoom In for Enhanced Multimodal Text-Rich Image Understanding”.☆25Updated 2 months ago
- ☆39Updated 4 years ago
- Empirical Study Towards Building An Effective Multi-Modal Large Language Model☆23Updated 10 months ago
- ☆25Updated 3 years ago
- Vision-Language Pre-Training for Boosting Scene Text Detectors (CVPR2022)☆11Updated 2 years ago
- ☆34Updated 3 months ago
- [PR 2024] A large Cross-Modal Video Retrieval Dataset with Reading Comprehension☆18Updated 8 months ago
- PyTorch implementation of BMVC2022 paper Masked Vision-Language Transformers for Scene Text Recognition☆29Updated last year
- imagetokenizer is a python package, helps you encoder visuals and generate visuals token ids from codebook, supports both image and video…☆19Updated 2 months ago
- ☆16Updated 2 years ago
- ☆52Updated this week
- Unconstrained Text Detection with Box Supervisionand Dynamic Self-Training☆33Updated last year
- Official implementation of High Fidelity Scene Text Synthesis.☆33Updated 3 weeks ago
- Exploration of the multi modal fuyu-8b model of Adept. 🤓 🔍☆28Updated 10 months ago
- [FGVC9-CVPR 2022] The second place solution for 2nd eBay eProduct Visual Search Challenge.☆26Updated 2 years ago
- convert paddleOCR to torchOCR, ppocr-v3,ppocr-v4, onnx, openvino☆30Updated last year
- An object detection codebase based on MegEngine.☆28Updated last year
- An open-source implementaion for fine-tuning Qwen2-VL-2B and Qwen2-VL-7B.☆33Updated this week
- ☆63Updated last year