Bottom-up attention model for image captioning and VQA, based on Faster R-CNN and Visual Genome
- vqa
- visual-question-answering
- captioning-images
- faster-rcnn
132,241 visible repositories in the index
1–2 of 2 · Most stars
Bottom-up attention model for image captioning and VQA, based on Faster R-CNN and Visual Genome
An efficient PyTorch implementation of the winning entry of the 2017 VQA Challenge.