Abstract | ||
---|---|---|
With the recent resurgence of neural networks and the proliferation of massive amounts of unlabeled multimodal data, recommendation systems and multimodal retrieval systems based on continuous representation spaces and deep learning methods are becoming of great interest. Multimodal representations are typically obtained with autoencoders that reconstruct multimodal data. In this article, we descr... |
Year | DOI | Venue |
---|---|---|
2018 | 10.1109/MMUL.2018.023121161 | IEEE MultiMedia |
Keywords | Field | DocType |
Computer architecture,Task analysis,Neural networks,Visualization,Streaming media,Hypertext systems,Training | Crossmodal,Recommender system,Computer science,Visualization,Human–computer interaction,Encoder,Artificial intelligence,Hyperlink,Deep learning,Artificial neural network,Benchmarking | Journal |
Volume | Issue | ISSN |
25 | 2 | 1070-986X |
Citations | PageRank | References |
1 | 0.35 | 0 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Vedran Vukotic | 1 | 29 | 4.59 |
christian raymond | 2 | 118 | 13.80 |
guillaume gravier | 3 | 1413 | 127.38 |