https://github.com/peteanderson80/bottom-up-attention

Bottom-up attention model for image captioning and VQA, based on Faster R-CNN and Visual Genome
https://github.com/peteanderson80/bottom-up-attention

caffe captioning-images faster-rcnn image-captioning mscoco mscoco-dataset visual-question-answering vqa

Last synced: about 1 month ago
JSON representation

Bottom-up attention model for image captioning and VQA, based on Faster R-CNN and Visual Genome

• Host: GitHub
• URL: https://github.com/peteanderson80/bottom-up-attention
• Owner: peteanderson80
• License: mit
• Created: 2017-05-26T23:00:39.000Z (over 7 years ago)
• Default Branch: master
• Last Pushed: 2023-02-03T04:27:32.000Z (over 1 year ago)
• Last Synced: 2024-04-16T05:50:34.563Z (5 months ago)
• Topics: caffe, captioning-images, faster-rcnn, image-captioning, mscoco, mscoco-dataset, visual-question-answering, vqa
• Language: Jupyter Notebook
• Homepage: http://panderson.me/up-down-attention/
• Size: 13.4 MB
• Stars: 1,401
• Watchers: 26
• Forks: 378
• Open Issues: 68
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project