meiyor/DeepGaze-Text-Embedding-Map
DeepGaze + Text-Embedding-Map project developed in Cardiff University - Christoph Teufel Lab
This project helps researchers and scientists better predict where people will look in an image by incorporating semantic information about the objects and scenes. It takes in images and human gaze fixation data, along with text descriptions of objects and scenes, to produce more accurate predictions of visual attention patterns. This tool is for cognitive scientists, vision researchers, and anyone studying human visual perception.
No commits in the last 6 months.
Use this if you need to create more robust and semantically-aware models for predicting human eye movements on images.
Not ideal if you are looking for a pre-trained, plug-and-play solution for general image saliency prediction without needing to train custom models or integrate detailed semantic information.
Stars
7
Forks
—
Language
Python
License
—
Category
Last pushed
May 31, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/meiyor/DeepGaze-Text-Embedding-Map"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
rmovva/HypotheSAEs
HypotheSAEs: hypothesizing interpretable relationships in text datasets using sparse...
interpretml/interpret-text
A library that incorporates state-of-the-art explainers for text-based machine learning models...
fdalvi/NeuroX
A Python library that encapsulates various methods for neuron interpretation and analysis in...
jalammar/ecco
Explain, analyze, and visualize NLP language models. Ecco creates interactive visualizations...
alexdyysp/ESIM-pytorch
中国高校计算机大赛--大数据挑战赛