abhshkdz/neural-vqa-attention
:question: Attention-based Visual Question Answering in Torch
This project helps computer vision researchers and AI developers build systems that can understand images and answer questions about them. It takes an image and a natural language question as input, then produces a text answer along with a 'heatmap' showing where in the image the model focused its attention to derive that answer. It's designed for those exploring visual question answering models and their interpretability.
101 stars. No commits in the last 6 months.
Use this if you need a straightforward, interpretable model to understand how a system 'looks' at an image to answer a question, rather than needing the absolute highest accuracy.
Not ideal if you require state-of-the-art accuracy for highly sensitive or critical visual question answering applications.
Stars
101
Forks
34
Language
Jupyter Notebook
License
—
Category
Last pushed
Aug 13, 2017
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/abhshkdz/neural-vqa-attention"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
open-mmlab/mmpretrain
OpenMMLab Pre-training Toolbox and Benchmark
facebookresearch/mmf
A modular framework for vision & language multimodal research from Facebook AI Research (FAIR)
adambielski/siamese-triplet
Siamese and triplet networks with online pair/triplet mining in PyTorch
HuaizhengZhang/Awsome-Deep-Learning-for-Video-Analysis
Papers, code and datasets about deep learning and multi-modal learning for video analysis
KaiyangZhou/pytorch-vsumm-reinforce
Unsupervised video summarization with deep reinforcement learning (AAAI'18)