Papers with fusion of linguistic features
Language-Conditioned Feature Pyramids for Visual Selection Tasks (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Referring expression comprehension is the ability to locate language to an object in an image. |
| Approach: | They propose a neural network architecture that modulates visual features with varying sizes of receptive field by linguistic features and a visual dialogue game to generate referring expression comprehension. |
| Outcome: | The proposed architecture is able to modulate visual features with varying sizes of receptive field by linguistic features on two visual dialogue games. |