Video captioning is an advanced multi-modal task which aims to describe a
video clip using a natural language sentence. The encoder-decoder framework is
the most popular paradigm for this task in recent years. However, there exist
some problems in the decoder of a video captioning model. We make a thorough
investigation into the decoder and adopt three techniques to improve the
performance of the model. First of all, a combination of variational dropout
and layer normalization is embedded into a recurrent unit to alleviate the
problem of overfitting. Secondly, a new online method is proposed to evaluate
the performance of a model on a validation set so as to select the best
checkpoint for testing. Finally, a new training strategy called professional
learning is proposed which uses the strengths of a captioning model and
bypasses its weaknesses. It is demonstrated in the experiments on Microsoft
Research Video Description Corpus (MSVD) and MSR-Video to Text (MSR-VTT)
datasets that our model has achieved the best results evaluated by BLEU, CIDEr,
METEOR and ROUGE-L metrics with significant gains of up to 18% on MSVD and 3.5%
on MSR-VTT compared with the previous state-of-the-art models.

本篇研究针对视频字幕模型的解码问题，通过三种技术改进模型的性能，包括使用变分 Dropout 和层归一化改善过拟合问题、提出在线评估模型性能以选择最佳测试检查点的方法、提出专业学习的新训练策略。在 Microsoft Research Video Description Corpus (MSVD) 和 MSR-Video to Text (MSR-VTT) 数据集上进行的实验证明，相较于之前最先进的模型，我们的模型在 BLEU、CIDEr、METEOR 和 ROUGE-L 指标上获得了显著的成果，其中在 MSVD 数据集上提升了高达 18%，在 MSR-VTT 数据集上提升了 3.5%。