Clue: Cross-modal Coherence Modeling for Caption Generation
This work addresses the challenge of improving image captioning for applications requiring coherent and goal-oriented descriptions, though it is incremental as it builds on existing discourse models.
The paper tackled the problem of generating more consistent and higher-quality image captions by modeling cross-modal coherence relations, resulting in dramatic improvements in caption consistency and quality.
We use coherence relations inspired by computational models of discourse to study the information needs and goals of image captioning. Using an annotation protocol specifically devised for capturing image--caption coherence relations, we annotate 10,000 instances from publicly-available image--caption pairs. We introduce a new task for learning inferences in imagery and text, coherence relation prediction, and show that these coherence annotations can be exploited to learn relation classifiers as an intermediary step, and also train coherence-aware, controllable image captioning models. The results show a dramatic improvement in the consistency and quality of the generated captions with respect to information needs specified via coherence relations.