Delving Deeper into the Decoder for Video Captioning

Abstract

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.

arXiv comment8 pages, 3 figures, European Conference on Artificial Intelligence. ECAI 2020

References in corpus (10)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Neural Machine Translation by Jointly Learning to Align and Translate
• Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
• Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
• Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning
• Recurrent Neural Network Regularization
• Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks
• A Theoretically Grounded Application of Dropout in Recurrent Neural Networks
• Multiple Object Recognition with Visual Attention
• How (not) to Train your Generative Model: Scheduled Sampling, Likelihood, Adversary?