Text-guided Attention Model for Image Captioning
This work addresses the challenge of distinguishing small or confusable objects in image captioning for applications like accessibility and content description.
The paper tackles the problem of generating detailed image captions by introducing a text-guided attention model that uses associated captions to steer visual attention, achieving state-of-the-art performance on the MS-COCO benchmark.
Visual attention plays an important role to understand images and demonstrates its effectiveness in generating natural language descriptions of images. On the other hand, recent studies show that language associated with an image can steer visual attention in the scene during our cognitive process. Inspired by this, we introduce a text-guided attention model for image captioning, which learns to drive visual attention using associated captions. For this model, we propose an exemplar-based learning approach that retrieves from training data associated captions with each image, and use them to learn attention on visual features. Our attention model enables to describe a detailed state of scenes by distinguishing small or confusable objects effectively. We validate our model on MS-COCO Captioning benchmark and achieve the state-of-the-art performance in standard metrics.