Every Picture Tells a Story: Generating Sentences from Images

@inproceedings{Farhadi2010EveryPT,
  title={Every Picture Tells a Story: Generating Sentences from Images},
  author={Ali Farhadi and M. Hejrati and M. Sadeghi and Peter Young and Cyrus Rashtchian and J. Hockenmaier and D. Forsyth},
  booktitle={ECCV},
  year={2010}
}
Humans can prepare concise descriptions of pictures, focusing on what they find important. [...] Key Method The score is obtained by comparing an estimate of meaning obtained from the image to one obtained from the sentence. Each estimate of meaning comes from a discriminative procedure that is learned us-ingdata. We evaluate on a novel dataset consisting of human-annotated images. While our underlying estimate of meaning is impoverished, it is sufficient to produce very good quantitative results, evaluated…Expand
882 Citations

Figures, Tables, and Topics from this paper

Automatic sentence generation from images
  • 17
  • Highly Influenced
  • PDF
A Hierarchical Approach for Generating Descriptive Image Paragraphs
  • 178
  • PDF
Framing Image Description as a Ranking Task: Data, Models and Evaluation Metrics (Extended Abstract)
  • 781
  • PDF
Understanding images with natural sentences
  • 9
  • PDF
Large Scale Retrieval and Generation of Image Descriptions
  • 48
  • PDF
Choosing Linguistics over Vision to Describe Images
  • 86
  • Highly Influenced
  • PDF
DISCO: Describing Images Using Scene Contexts and Objects
  • 7
  • PDF
Show and tell: A neural image caption generator
  • 3,814
  • PDF
Grounded Compositional Semantics for Finding and Describing Images with Sentences
  • 718
  • PDF
Composing Simple Image Descriptions using Web-scale N-grams
  • 289
  • PDF
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 40 REFERENCES
Clustering art
  • 188
  • PDF
Understanding videos, constructing plots learning a visually grounded storyline model from annotated videos
  • 134
  • PDF
Towards total scene understanding: Classification, annotation and segmentation in an automatic framework
  • 415
  • PDF
I2T: Image Parsing to Text Description
  • 262
  • PDF
WordsEye: an automatic text-to-scene conversion system
  • 421
  • PDF
Learning realistic human actions from movies
  • 3,459
  • PDF
Improving People Search Using Query Expansions
  • 31
  • PDF
...
1
2
3
4
...