Image Captioning: Transforming Objects into Words
This work addresses image captioning for AI applications, but it is incremental as it builds upon existing object detection-based methods.
The paper tackled the problem of generating captions from images by incorporating spatial relationships between detected objects, resulting in improvements across all common captioning metrics on the MS-COCO dataset.
Image captioning models typically follow an encoder-decoder architecture which uses abstract image feature vectors as input to the encoder. One of the most successful algorithms uses feature vectors extracted from the region proposals obtained from an object detector. In this work we introduce the Object Relation Transformer, that builds upon this approach by explicitly incorporating information about the spatial relationship between input detected objects through geometric attention. Quantitative and qualitative results demonstrate the importance of such geometric attention for image captioning, leading to improvements on all common captioning metrics on the MS-COCO dataset.