vision-longformer
Image encoder
An implementation of a vision transformer architecture designed for high-resolution image encoding with multiple efficient attention mechanisms
243 stars
12 watching
25 forks
Language: Python
last commit: almost 3 years ago
Linked from 1 awesome list
weiaicunzai/awesome-image-classificationRelated projects:
| Repository | Description | Stars |
|---|---|---|
 webmproject/libwebp | A C-based library and command line tools for encoding and decoding image formats commonly used on the web. | 2,042 |
 gordonhu608/mqt-llava | A vision-language model that uses a query transformer to encode images as visual tokens and allows flexible choice of the number of visual tokens. | 101 |
| microsoft/cvt | An implementation of a new neural network architecture that combines the strengths of convolutional and transformer designs to improve performance on image classification tasks. | 559 |
 leeburrows/async-image-encoders | A library of classes for asynchronously encoding BitmapData objects into image file formats. | 19 |
 luoweizhou/vlp | A project for pre-training models to support image captioning and question answering tasks. | 416 |
 vision-cair/longvu | An artificial intelligence system designed to understand and describe long-form video content | 329 |
 lvandeve/lodepng | A PNG encoder and decoder written in C++ with support for ANSI C | 2,120 |
 slsfi/abbi-ng-ai-image-descriptor | An Angular web app for generating AI-generated image descriptions using OpenAI models | 1 |
 aomediacodec/libavif | A C library for encoding and decoding AV1 image files | 1,589 |
 pnggroup/libpng | A Portable Network Graphics (PNG) image format implementation with support for compression and decompression. | 1,315 |
 randy408/libspng | A lightweight PNG image decoder and encoder library with a focus on performance and simplicity. | 749 |
 ibm/max-image-resolution-enhancer | Enhances image resolution while adding realistic details using AI-powered super-resolution techniques | 994 |
 levydsa/qoiz | A software implementation of the QOI image format decoder and encoder in Zig. | 0 |
 google/jpegli | A JPEG encoder and decoder implementation with improved features and optimizations for image compression and decompression. | 139 |
| ibm/max-image-segmenter | An image segmentation system that identifies objects in an image and assigns each pixel to a particular object. | 32 |