Ask-Anything
VideoChat
An end-to-end chatbot for video and image interaction with various language models
[CVPR2024 Highlight][VideoChatGPT] ChatGPT with video understanding! And many more supported LMs such as miniGPT4, StableLM, and MOSS.
3k stars
37 watching
253 forks
Language: Python
last commit: 3 months ago
Linked from 4 awesome lists
big-modelcaptioning-videoschatchatgptfoundation-modelsgradiolangchainlarge-language-modelslarge-modelstablelmvideovideo-question-answeringvideo-understanding
Related projects:
Repository | Description | Stars |
---|---|---|
| Provides a benchmarking framework and implementation for deep learning-based text recognition models | 3,769 |
| Software platform for analyzing medical images and predicting cancer outcomes through machine learning | 182 |
| Provides tools and algorithms to understand how machine learning models make predictions | 4,982 |
| Adds captchas to forms in web applications | 1,388 |
| A pure JavaScript solution for generating and validating image-based CAPTCHAs without relying on specific libraries or frameworks. | 465 |
| This project develops strategies to optimize in-context sequence configurations for Vision-Language few-shot learning, with a focus on exploring the effects of varying configurations on image-text pairs. | 33 |
| A system for solving opt-in CAPTCHAs by detecting text within images and classifying it using a trained model. | 653 |
| A collection of benchmarking tests for various programming languages | 2,825 |
| Compares performance of various data serialization libraries in C++ | 731 |
| A captcha solution designed to be fast and user-friendly, providing an easy alternative to traditional captchas. | 144 |
| A package that enables server-side verification of hCaptcha responses in ASP.NET Core Blazor applications. | 7 |
| Enhances language models to generate text based on visual descriptions of images | 352 |
| A comprehensive benchmarking framework for evaluating brain-computer interface algorithms on EEG datasets | 714 |
| A CAPTCHA solver that extracts and matches text from an image by calculating pixel differences between the input image and pre-computed letter masks. | 556 |
| A comprehensive collection of tools and techniques for breaking and recognizing various types of CAPTCHAs used in online services | 1,049 |