COMIC: Toward A Compact Image Captioning Model With Attention
Recent works in image captioning have shown very promising raw performance. However, we realize that most of these encoder-decoder style networks with attention do not scale naturally to large vocabulary size, making them difficult to deploy on embedded systems with limited hardware resources. This...
Hauptverfasser: | , , |
---|---|
Format: | Artikel |
Veröffentlicht: |
Institute of Electrical and Electronics Engineers (IEEE)
2019
|
Schlagworte: |