Image Captioning using Multiple Transformers for Self-Attention Mechanism
This addresses image captioning challenges for computer vision applications, but appears incremental as it builds on existing transformer-based methods.
The paper tackles real-time image captioning with adequate precision by proposing the Multiple Transformers for Self-Attention Mechanism (MTSM), which uses multiple transformers for self-attention and achieves results on the MSCOCO dataset.
Real-time image captioning, along with adequate precision, is the main challenge of this research field. The present work, Multiple Transformers for Self-Attention Mechanism (MTSM), utilizes multiple transformers to address these problems. The proposed algorithm, MTSM, acquires region proposals using a transformer detector (DETR). Consequently, MTSM achieves the self-attention mechanism by transferring these region proposals and their visual and geometrical features through another transformer and learns the objects' local and global interconnections. The qualitative and quantitative results of the proposed algorithm, MTSM, are shown on the MSCOCO dataset.