Framing image description as a ranking task

By HodoshMicah, YoungPeter, HockenmaierJulia. 2013

59 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Multimodal Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Chunyuan Li
2. Lawrence Carin
3. Zhe Gan
4. Afra Alishahi
5. Yunchen Pu
6. Grzegorz Chrupała
7. Changyou Chen
8. Lieke Gelderloos

In Multimodal Learning

1. Afra Alishahi
2. Chunyuan Li
3. Grzegorz Chrupała
4. Zhe Gan
5. Lawrence Carin
6. Lieke Gelderloos
7. Di Kang
8. Changyou Chen

Citations in the corpus

• Incorporating Side Information by Adaptive Convolution (2017, methodology): “We test on the Flickr8k (Hodosh et al. 2013) dataset, and randomly select 5000 images for training, 1400 images for validation, and another 1600 images for testing.”
• Scalable Bayesian Learning of Recurrent Neural Networks for Language Modeling (2016, result): “For example, pSGLD provides 2.77 BLEU-4 score improvement over RMSprop on the Flickr8k dataset.”
• Representations of language in a model of visually grounded speech signal (2017, methodology): “The Flickr8k Audio Caption Corpus was constructed by having crowdsource workers read aloud the captions in the original Flickr8K corpus (Hodosh et al., 2013).”