search

cesc-park / attend2u

🖼️ Attend to You: Personalized Image Captioning with Context Sequence Memory Networks. In CVPR, 2017. Expanded : Towards Personalized Image Captioning via Multimodal Memory Networks. In IEEE TPAMI, 2018.
MIT License
209 stars 57 forks source link

Difference between papers #11

Closed vedantc6 closed 5 years ago

vedantc6 commented 5 years ago

Hi @cesc-park If I am correct, the only difference between CVPR and TPAMI papers is use of data sets. Both use the same CSMN architecture. Can you or someone validate this?

cesc-park commented 5 years ago

The dataset is different and contains partial changes. The difference between the TPAMI and CVPR versions is in the CNN structure(shallow and wide cnn / deep CNN). The current code is the CVPR version, and the hyperparameters are set to run easily. You can use the same hyperparameters as CVPR by modifying them.

vedantc6 commented 5 years ago

Thanks a lot!