XduSyL/EventGPT
🔥[CVPR2025] EventGPT: Event Stream Understanding with Multimodal Large Language Models
This project helps operations engineers, automation specialists, or security analysts understand incredibly fast-moving events by analyzing high-speed event streams (data from specialized event cameras) combined with text. It takes in raw event data and a text query, then provides a detailed natural language description of what happened in the scene, even for actions occurring within 50 milliseconds. The end-user persona is someone who needs to interpret rapid visual occurrences for applications like industrial monitoring or anomaly detection.
104 stars. No commits in the last 6 months.
Use this if you need to interpret extremely rapid visual events, such as a droplet falling or a die spinning, that standard video cameras might miss or blur, and you want a natural language description of these movements.
Not ideal if your primary need is analyzing standard frame-based video or still images, or if you don't work with specialized event camera data that captures changes at millisecond speeds.
Stars
104
Forks
11
Language
Python
License
—
Category
Last pushed
Jul 26, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/XduSyL/EventGPT"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
jingyaogong/minimind-v
🚀 「大模型」1小时从0训练26M参数的视觉多模态VLM！🌏 Train a 26M-parameter VLM from scratch in just 1 hours!
roboflow/vision-ai-checkup
Take your LLM to the optometrist.
SkyworkAI/Skywork-R1V
Skywork-R1V is an advanced multimodal AI model series developed by Skywork AI, specializing in...
zai-org/GLM-TTS
GLM-TTS: Controllable & Emotion-Expressive Zero-shot TTS with Multi-Reward Reinforcement Learning
NExT-GPT/NExT-GPT
Code and models for ICML 2024 paper, NExT-GPT: Any-to-Any Multimodal Large Language Model