Image Captioning with Integrated Bottom-Up and Multi-level Residual Top-Down Attention for Game Scene Understanding
This work addresses game image captioning, a domain-specific problem with unique characteristics, but it is incremental as it builds on existing attention mechanisms.
The authors tackled game image captioning by integrating bottom-up attention with a new multi-level residual top-down attention mechanism to address spatial information loss and improve feature fusion, resulting in a model that outperforms existing baselines on two newly created game datasets.
Image captioning has attracted considerable attention in recent years. However, little work has been done for game image captioning which has some unique characteristics and requirements. In this work we propose a novel game image captioning model which integrates bottom-up attention with a new multi-level residual top-down attention mechanism. Firstly, a lower-level residual top-down attention network is added to the Faster R-CNN based bottom-up attention network to address the problem that the latter may lose important spatial information when extracting regional features. Secondly, an upper-level residual top-down attention network is implemented in the caption generation network to better fuse the extracted regional features for subsequent caption prediction. We create two game datasets to evaluate the proposed model. Extensive experiments show that our proposed model outperforms existing baseline models.