Text with Knowledge Graph Augmented Transformer for Video Captioning

TL;DR

This paper introduces TextKG, a two-stream transformer model augmented with knowledge graphs for improved video captioning, effectively addressing the long-tail words challenge and outperforming state-of-the-art methods on multiple datasets.

Contribution

The paper proposes a novel two-stream transformer architecture with external knowledge integration and cross attention for enhanced video captioning.

Findings

Outperforms state-of-the-art on four datasets

Improves CIDEr scores by 18.7% on YouCookII

Effectively mitigates long-tail words challenge

Abstract

Video captioning aims to describe the content of videos using natural language. Although significant progress has been made, there is still much room to improve the performance for real-world applications, mainly due to the long-tail words challenge. In this paper, we propose a text with knowledge graph augmented transformer (TextKG) for video captioning. Notably, TextKG is a two-stream transformer, formed by the external stream and internal stream. The external stream is designed to absorb additional knowledge, which models the interactions between the additional knowledge, e.g., pre-built knowledge graph, and the built-in information of videos, e.g., the salient object regions, speech transcripts, and video captions, to mitigate the long-tail words challenge. Meanwhile, the internal stream is designed to exploit the multi-modality information in videos (e.g., the appearance of video frames, speech transcripts, and video captions) to ensure the quality of caption results. In addition, the cross attention mechanism is also used in between the two streams for sharing information. In this way, the two streams can help each other for more accurate results. Extensive experiments conducted on four challenging video captioning datasets, i.e., YouCookII, ActivityNet Captions, MSRVTT, and MSVD, demonstrate that the proposed method performs favorably against the state-of-the-art methods. Specifically, the proposed TextKG method outperforms the best published results by improving 18.7% absolute CIDEr scores on the YouCookII dataset.