QQBrowserVideoSearch/CBVS-UniCLIP
A Large-Scale Chinese Image-Text Benchmark for Real-World Short Video Search Scenarios
This project helps improve the search experience for short videos by making them more discoverable through text queries. It takes short video cover images and their associated text (like titles or user queries) to create a robust system that can match video content with what users are searching for. This is primarily useful for platform managers, content curators, or product owners working on Chinese short video platforms.
No commits in the last 6 months.
Use this if you need to significantly enhance the accuracy of searching for Chinese short videos using text queries.
Not ideal if your primary content is long-form video, or if your user base does not primarily search in Chinese.
Stars
13
Forks
—
Language
Python
License
—
Category
Last pushed
Jan 24, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/QQBrowserVideoSearch/CBVS-UniCLIP"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
ClipsAI/clipsai
Clips AI is an open-source Python library that automatically converts long videos into clips.
ai-forever/ru-clip
CLIP implementation for Russian language
patrickjohncyh/fashion-clip
FashionCLIP is a CLIP-like model fine-tuned for the fashion domain.
Lednik7/CLIP-ONNX
It is a simple library to speed up CLIP inference up to 3x (K80 GPU)
suinleelab/CellCLIP
[NeurIPS 2025] CellCLIP – Learning Perturbation Effects in Cell Painting via Text-Guided...