{
  "id": "2001.05614",
  "version": "v1",
  "published": "2020-01-16T02:18:27.000Z",
  "updated": "2020-01-16T02:18:27.000Z",
  "title": "Delving Deeper into the Decoder for Video Captioning",
  "authors": [
    "Haoran Chen",
    "Jianmin Li",
    "Xiaolin Hu"
  ],
  "comment": "8 pages, 3 figures, European Conference on Artificial Intelligence",
  "categories": [
    "cs.CV",
    "cs.CL"
  ],
  "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 still exist some non-negligible 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 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 \\textit{professional learning} is proposed which develops the strong points 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 11.7% on MSVD and 5% on MSR-VTT compared with the previous state-of-the-art models.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2020-01-16T02:18:27.000Z"
    }
  ],
  "analyses": {
    "subjects": [
      "68T45",
      "68T50",
      "I.2.7"
    ],
    "keywords": [
      "video captioning",
      "delving deeper",
      "microsoft research video description corpus",
      "captioning model",
      "natural language sentence"
    ],
    "tags": [
      "conference paper"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 8,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}