AIPython★ 293
mbzuai-oryx/VideoGPT-plus
VIDEO GPT-PLUS: ADVANCED VIDEO UNDERSTANDING
Official repository of the VideoGPT+ paper: combines image and video encoders for improved video understanding. Enables extracting semantic features, generating descriptions, and answering video questions using GPT-4o.
// KEY FEATURES
- Extracts joint image‑video features via dual‑encoder for precise video search.
- Generates video descriptions in natural language from extracted features using GPT-4o.
- Answers complex video‑content questions using context from frames and text.
- Supports fine‑tuning on custom data for video‑understanding tasks.
#chatbot#clip#dual-encoder#gpt4#gpt4o#image-encoder#llama3#llava#multimodal#phi-3-mini#vicuna#video-chatbot
Open on GitHub →New repositories every 30 minutes
REDDYX AI scans GitHub 24/7 and ships the best AI/ML/Web3 projects to Telegram.
Join on Telegram