Improving Image Captioning with Better Use of Captions

by   Zhan Shi, et al.

Image captioning is a multimodal problem that has drawn extensive attention in both the natural language processing and computer vision community. In this paper, we present a novel image captioning architecture to better explore semantics available in captions and leverage that to enhance both image representation and caption generation. Our models first construct caption-guided visual relationship graphs that introduce beneficial inductive bias using weakly supervised multi-instance learning. The representation is then enhanced with neighbouring and contextual nodes with their textual and visual features. During generation, the model further incorporates visual relationships using multi-task learning for jointly predicting word and object/predicate tag sequences. We perform extensive experiments on the MSCOCO dataset, showing that the proposed framework significantly outperforms the baselines, resulting in the state-of-the-art performance under a wide range of evaluation metrics.



There are no comments yet.


page 9


UIT-ViIC: A Dataset for the First Evaluation on Vietnamese Image Captioning

Image Captioning, the task of automatic generation of image captions, ha...

Dependent Multi-Task Learning with Causal Intervention for Image Captioning

Recent work for image captioning mainly followed an extract-then-generat...

HorNet: A Hierarchical Offshoot Recurrent Network for Improving Person Re-ID via Image Captioning

Person re-identification (re-ID) aims to recognize a person-of-interest ...

Bench-Marking And Improving Arabic Automatic Image Captioning Through The Use Of Multi-Task Learning Paradigm

The continuous increase in the use of social media and the visual conten...

Figure Captioning with Reasoning and Sequence-Level Training

Figures, such as bar charts, pie charts, and line plots, are widely used...

Aligning Visual Regions and Textual Concepts: Learning Fine-Grained Image Representations for Image Captioning

In image-grounded text generation, fine-grained representations of the i...

MRRC: Multiple Role Representation Crossover Interpretation for Image Captioning With R-CNN Feature Distribution Composition (FDC)

While image captioning through machines requires structured learning and...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.