Generating multi-sentence descriptions for videos is one of the most
challenging captioning tasks due to its high requirements for not only visual
relevance but also discourse-based coherence across the sentences in the
paragraph. Towards this goal, we propose a new approach called Memory-Augmented
Recurrent Transformer (MART), which uses a memory module to augment the
transformer architecture. The memory module generates a highly summarized
memory state from the video segments and the sentence history so as to help
better prediction of the next sentence (w.r.t. coreference and repetition
aspects), thus encouraging coherent paragraph generation. Extensive
experiments, human evaluations, and qualitative analyses on two popular
datasets ActivityNet Captions and YouCookII show that MART generates more
coherent and less repetitive paragraph captions than baseline methods, while
maintaining relevance to the input video events. All code is available
open-source at: this https URL

我们提出了一种新的方法 Memory-Augmented Recurrent Transformer (MART)，它使用记忆模块来增强 Transformer 的结构，以更好地预测下一句话（关于指代和重复），从而鼓励连贯的段落生成。实验证明，MART 生成的段落字幕比基线方法更连贯，更少重复，并保持与输入视频事件的相关性。