Multimodal Neural Language Models
Ryan Kiros, Ruslan Salakhutdinov, Rich Zemel · 2014
This paper focuses on multimodal neural language models: models of natural language that can be conditional on other modalities Can perform image retrival from text, as well as generating text or text retrival given an image
Cited by 516 works.
Authors
References
- ImageNet classification with deep convolutional neural networks
- BLEU
- Efficient Estimation of Word Representations in Vector Space
- DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
- A unified architecture for natural language processing
- Modeling the Shape of the Scene: A Holistic Representation of the Spatial Envelope
- Recurrent neural network based language model
- 10.1162/153244303322533223
- Word Representations: A Simple and General Method for Semi-Supervised Learning
- A Scalable Hierarchical Distributed Language Model