Mar 22, 2023 · In this paper, we propose a text with knowledge graph augmented transformer (TextKG) for video captioning.

This repository provides the code and resources associated with our paper titled Text with Knowledge Graph Augmented Transformer for Video Captioning.

Video captioning aims to describe the content of videos using natural language. Although significant progress has been made, there is still much room to ...

In this paper, we propose a text with knowledge graph augmented transformer (TextKG)for video captioning.

Existing video captioning methods generally have long tail problems. We present TextKG, a knowledge graph (KG) augmented transformer for video captioning, which ...

Gu et al. [27] introduced a transformer based approach for video captioning. The knowledge graph augmentation transformer (TextKG) is designed to capture the ...

Mar 22, 2023 · A simple yet effective end-to-end transformer in the compressed domain for video captioning that enables learning from the compressed video for captioning.

Duration: 4:14
Posted: Jun 1, 2023

The proposed method, called TextKG, uses additional knowledge in the form of a knowledge graph and multi-modality information in videos to improve video ...

60.8, 30.5, 64.8, 46.6. Text with Knowledge Graph Augmented Transformer for Video Captioning ... Video-Language Transformers with Masked Visual Modeling. 2022.