Skip to content

Code Release for `Learning Answer Embeddings for Visual Question Answering`. (CVPR 2018)

License

Notifications You must be signed in to change notification settings

hexiang-hu/answer_embedding

Repository files navigation

Answer Embedding

Code Release for Learning Answer Embeddings for Visual Question Answering. (CVPR 2018)

Usage

usage: train_v7w_embedding.py [-h] [--gpu_id GPU_ID] [--batch_size BATCH_SIZE]
                              [--max_negative_answer MAX_NEGATIVE_ANSWER]
                              [--answer_batch_size ANSWER_BATCH_SIZE]
                              [--loss_temperature LOSS_TEMPERATURE]
                              [--pretrained_model PRETRAINED_MODEL]
                              [--context_embedding {SAN,BoW}]
                              [--answer_embedding {BoW,RNN}] [--name NAME]

optional arguments:
  -h, --help            show this help message and exit
  --gpu_id GPU_ID
  --batch_size BATCH_SIZE
  --max_negative_answer MAX_NEGATIVE_ANSWER
  --answer_batch_size ANSWER_BATCH_SIZE
  --loss_temperature LOSS_TEMPERATURE
  --pretrained_model PRETRAINED_MODEL
  --context_embedding {SAN,BoW}
  --answer_embedding {BoW,RNN}
  --name NAME

Bibtex

Please cite with the following bibtex if you are using any related resource of this repo for your research.

@inproceedings{hu2018learning,
  title={Learning Answer Embeddings for Visual Question Answering},
  author={Hu, Hexiang and Chao, Wei-Lun and Sha, Fei},
  booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
  pages={5428--5436},
  year={2018}
}

Acknowledgement

Part of this code uses components from pytorch-vqa and torchtext. We thank authors for releasing their code.

References

  1. Being Negative but Constructively: Lessons Learnt from Creating Better Visual Question Answering Datasets (qaVG website)
  2. Visual7W: Grounded Question Answering in Images (website)
  3. Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering website

About

Code Release for `Learning Answer Embeddings for Visual Question Answering`. (CVPR 2018)

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published