Corpus ID: 43920307

Generating Video Description using RNN with Semantic Attention

@inproceedings{Natsuda2017GeneratingVD,
  title={Generating Video Description using RNN with Semantic Attention},
  author={Laokulrat Natsuda and Okazaki Naoaki and Nakayama Hideki},
  year={2017}
}
Being able to understand videos can have a great impact and can be useful to many other applications. However, generated descriptions by computers often fail to mention correct objects appearing in videos. This work aims to alleviate this problem by including external fine-grained visual information detected from all video frames. In this paper, we propose an LSTM-based sequence-tosequence model with semantic attention for video description generation. The results show that using semantic… Expand
1 Citations
Describing human activities in video streams
  • PDF

References

SHOWING 1-10 OF 11 REFERENCES
Translating Videos to Natural Language Using Deep Recurrent Neural Networks
  • 574
  • Highly Influential
Sequence to Sequence -- Video to Text
  • 920
  • Highly Influential
  • PDF
Image Captioning with Semantic Attention
  • 984
  • PDF
From captions to visual concepts and back
  • 997
  • PDF
Show and tell: A neural image caption generator
  • 3,764
  • PDF
Very Deep Convolutional Networks for Large-Scale Image Recognition
  • 46,865
  • PDF
Microsoft COCO Captions: Data Collection and Evaluation Server
  • 832
  • PDF
Caffe: Convolutional Architecture for Fast Feature Embedding
  • 12,695
  • PDF
Glove: Global Vectors for Word Representation
  • 17,318
  • PDF
Collecting Highly Parallel Data for Paraphrase Evaluation
  • 507
  • Highly Influential
  • PDF
...
1
2
...