Unifying Visual-Semantic Embeddings with Multimodal Neural Language Models
This work addresses multimodal learning challenges for applications like image captioning and retrieval, but it is incremental as it builds on existing encoder-decoder and neural language model frameworks.
The paper tackles the problem of learning a joint embedding space for images and text and generating novel descriptions, achieving state-of-the-art performance on Flickr8K and Flickr30K datasets without using object detections, and demonstrating multimodal regularities through vector space arithmetic.
Inspired by recent advances in multimodal learning and machine translation, we introduce an encoder-decoder pipeline that learns (a): a multimodal joint embedding space with images and text and (b): a novel language model for decoding distributed representations from our space. Our pipeline effectively unifies joint image-text embedding models with multimodal neural language models. We introduce the structure-content neural language model that disentangles the structure of a sentence to its content, conditioned on representations produced by the encoder. The encoder allows one to rank images and sentences while the decoder can generate novel descriptions from scratch. Using LSTM to encode sentences, we match the state-of-the-art performance on Flickr8K and Flickr30K without using object detections. We also set new best results when using the 19-layer Oxford convolutional network. Furthermore we show that with linear encoders, the learned embedding space captures multimodal regularities in terms of vector space arithmetic e.g. *image of a blue car* - "blue" + "red" is near images of red cars. Sample captions generated for 800 images are made available for comparison.