CFSum: A Coarse-to-Fine Contribution Network for Multimodal Summarization
This work addresses the challenge of effectively integrating visual information in multimodal summarization for applications like news or social media analysis, representing an incremental advance by refining existing fusion methods.
The paper tackles the problem of unclear visual modality contributions in multimodal summarization by proposing CFSum, a coarse-to-fine contribution network that filters useless images and uses visual complement modules to guide attention, resulting in significant performance improvements over strong baselines on a standard benchmark.
Multimodal summarization usually suffers from the problem that the contribution of the visual modality is unclear. Existing multimodal summarization approaches focus on designing the fusion methods of different modalities, while ignoring the adaptive conditions under which visual modalities are useful. Therefore, we propose a novel Coarse-to-Fine contribution network for multimodal Summarization (CFSum) to consider different contributions of images for summarization. First, to eliminate the interference of useless images, we propose a pre-filter module to abandon useless images. Second, to make accurate use of useful images, we propose two levels of visual complement modules, word level and phrase level. Specifically, image contributions are calculated and are adopted to guide the attention of both textual and visual modalities. Experimental results have shown that CFSum significantly outperforms multiple strong baselines on the standard benchmark. Furthermore, the analysis verifies that useful images can even help generate non-visual words which are implicitly represented in the image.