Corpus ID: 2414468

DeepDiary: Automatic Caption Generation for Lifelogging Image Streams

@article{Fan2016DeepDiaryAC,
  title={DeepDiary: Automatic Caption Generation for Lifelogging Image Streams},
  author={Chenyou Fan and David J. Crandall},
  journal={ArXiv},
  year={2016},
  volume={abs/1608.03819}
}
Lifelogging cameras capture everyday life from a first-person perspective, but generate so much data that it is hard for users to browse and organize their image collections effectively. In this paper, we propose to use automatic image captioning algorithms to generate textual representations of these collections. We develop and explore novel techniques based on deep learning to generate captions for both individual images and image streams, using temporal consistency constraints to create… Expand
2 Citations
Towards Personalized Image Captioning via Multimodal Memory Networks
  • 18

References

SHOWING 1-10 OF 58 REFERENCES
DeepDiary: Automatically Captioning Lifelogging Image Streams
  • 8
  • PDF
Show and tell: A neural image caption generator
  • 3,739
  • Highly Influential
  • PDF
Aligning Books and Movies: Towards Story-Like Visual Explanations by Watching Movies and Reading Books
  • 895
  • PDF
Deep visual-semantic alignments for generating image descriptions
  • 1,895
  • Highly Influential
Deep Fragment Embeddings for Bidirectional Image Sentence Mapping
  • 640
  • PDF
CIDEr: Consensus-based image description evaluation
  • 1,530
  • PDF
Passively recognising human activities through lifelogging
  • 125
  • PDF
PlaceAvoider: Steering First-Person Cameras away from Sensitive Spaces
  • 112
  • PDF
Microsoft COCO: Common Objects in Context
  • 12,584
  • PDF
Sequence to Sequence -- Video to Text
  • 915
  • Highly Influential
  • PDF
...
1
2
3
4
5
...