CVCLJan 16, 2020

Delving Deeper into the Decoder for Video Captioning

arXiv:2001.05614v338 citations
AI Analysis

This work addresses decoder inefficiencies in video captioning, an incremental improvement for multi-modal AI applications.

The paper tackled problems in the decoder of video captioning models by introducing three techniques—variational dropout with layer normalization, an online validation method, and a professional learning strategy—resulting in state-of-the-art performance with gains of up to 18% on MSVD and 3.5% on MSR-VTT datasets.

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.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes