Name
Abstract | ||
|---|---|---|
We present a new tensor product generation network (TPGN) that generates natural language descriptions for images. The model has a novel architecture that instantiates a general framework for encoding and processing symbolic structure through neural network computation. This framework is built on Tensor Product Representations (TPRs). We evaluated the proposed TPGN on the MS COCO image captioning task. The experimental results show that the TPGN outperforms the LSTM based state-of-the-art baseline with a significant margin. Further, we show that our caption generation model can be interpreted as generating sequences of grammatical categories and retrieving words by their categories from a plan encoded as a distributed representation. |
Year | Venue | Field |
|---|---|---|
2017 | arXiv: Computer Vision and Pattern Recognition | Tensor product network,Tensor product,Grammatical category,Closed captioning,Pattern recognition,Computer science,Natural language,Artificial intelligence,Artificial neural network,Machine learning,Computation,Encoding (memory) |
DocType | Volume | Citations |
Journal | abs/1709.09118 | 0 |
PageRank | References | Authors |
0.34 | 0 | 5 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Qiuyuan Huang | 1 | 176 | 17.66 |
| Paul Smolensky | 2 | 215 | 93.76 |
| Xiaodong He | 3 | 3858 | 190.28 |
| Deng, Li | 4 | 9691 | 728.14 |
| Dapeng Wu | 5 | 4463 | 325.77 |