natural-language-youtube-search
natural-language-image-search
| natural-language-youtube-search | natural-language-image-search | |
|---|---|---|
| 6 | 9 | |
| 895 | 927 | |
| - | - | |
| 0.0 | 0.0 | |
| over 2 years ago | over 1 year ago | |
| Jupyter Notebook | Jupyter Notebook | |
| MIT License | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
natural-language-youtube-search
-
Show HN: Sieve: We processed 24 hours of video in
Just pass this through openai clip and you would get a semantic search without much effort. For example this is for youtube videos - https://github.com/haltakov/natural-language-youtube-search
- Search inside YouTube videos using natural language
-
OpenAI’s CLIP: Search Images with Descriptions Instead of Keywords
CLIP Video Search
- Show HN: Search inside YouTube videos using natural language queries
- Search inside YouTube videos using natural language queries
natural-language-image-search
-
I Built an Image Search Engine Using OpenAI Clip and Images from Wikimedia
You have the option of deleting and posting again I think. Anyways good luck.
Wikimedia search seems to work better for most searches I tried, possibly because of the manual tags etc.
https://imagioo.com/?q=astronaut+with+american+flag
https://commons.wikimedia.org/wiki/Special:MediaSearch?type=...
You might want to include examples where your search is better or just a faq on how to use it.
Nice idea though. It does seem to come in handy when you don't have descriptions of images. Eg: https://github.com/haltakov/natural-language-image-search
-
Simplest way to obtain a network classifying images as Paintings / Not Paintings?
You can give OpenAI's CLIP a shot: https://github.com/openai/CLIP. It's capable of doing zero-shot classification. Here is a neat example of CLIP usage: https://github.com/haltakov/natural-language-image-search.
-
[P] *Semantic* Video Search with OpenAI’s CLIP Neural Network
Does this use the same codebase as https://github.com/haltakov/natural-language-image-search ? Or do you have a different approach?
- Show HN: Search photos using natural language
- Show HN: Search photos on Unsplash using natural language queries
-
OpenAI’s CLIP: Search Images with Descriptions Instead of Keywords
CLIP Image Search
-
Search inside YouTube videos using natural language queries
Yes, this is definitely possible. You can maybe try computing some kind of image distance between frames or some keyframe extraction.
Once you compute the features, the search is very efficient! I tried it for searching in the 2M photos dataset from Unsplash and it takes like 2-3 seconds: https://github.com/haltakov/natural-language-image-search
I plan to run my personal photos through it :)
- Use OpenAI’s CLIP to search 2M photos on Unsplash
What are some alternatives?
CLIP - CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image
Queryable - Run OpenAI's CLIP model on iOS to search photos.
fastbook - The fastai book, published as Jupyter Notebooks
TargetCLIP - [ECCV 2022] Official PyTorch implementation of the paper Image-Based CLIP-Guided Essence Transfer.
steam-image-search - Search for images on Steam using natural language queries.
datasets - 🎁 5,400,000+ Unsplash images made available for research and machine learning