Semi-supervised multimodal coreference resolution in image narrations
This addresses the problem of fine-grained image-text alignment and ambiguity in narrative language for researchers in multimodal AI, but it is incremental as it builds on existing semi-supervised methods.
The paper tackled multimodal coreference resolution in image narrations by proposing a semi-supervised approach, which outperformed strong baselines in both coreference resolution and narrative grounding tasks.
In this paper, we study multimodal coreference resolution, specifically where a longer descriptive text, i.e., a narration is paired with an image. This poses significant challenges due to fine-grained image-text alignment, inherent ambiguity present in narrative language, and unavailability of large annotated training sets. To tackle these challenges, we present a data efficient semi-supervised approach that utilizes image-narration pairs to resolve coreferences and narrative grounding in a multimodal context. Our approach incorporates losses for both labeled and unlabeled data within a cross-modal framework. Our evaluation shows that the proposed approach outperforms strong baselines both quantitatively and qualitatively, for the tasks of coreference resolution and narrative grounding.