Name
Title | ||
|---|---|---|
Hierarchical Multimodal Attention for End-to-End Audio-Visual Scene-Aware Dialogue Response Generation |
Abstract | ||
|---|---|---|
•Hierarchical attention, including question self-attention and question-guided attention on input helps to improve the model performance.•Features of multiple modalities can be fused through nonlinear approaches for better contextual representations.•Input video length, question types in user queries, and turn positions affect the quality of the generated responses. |
Year | DOI | Venue |
|---|---|---|
2020 | 10.1016/j.csl.2020.101095 | Computer Speech & Language |
Keywords | DocType | Volume |
Dialogue system,Audio-visual scene-aware dialogue,Neural network,Multimodal attention,Response generation | Journal | 63 |
ISSN | Citations | PageRank |
0885-2308 | 0 | 0.34 |
References | Authors | |
0 | 4 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Hung Le | 1 | 3 | 3.09 |
| Doyen Sahoo | 2 | 83 | 9.94 |
| Nancy F. Chen | 3 | 120 | 28.98 |
| Steven C. H. Hoi | 4 | 3830 | 174.61 |