2 |
Something-Else: Compositional Action Recognition with Spatial-Temporal Interaction Networks ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
Learning to Reason: End-to-End Module Networks for Visual Question Answering ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
Natural-language video description with deep recurrent neural networks
|
|
|
|
BASE
|
|
Show details
|
|
6 |
Modeling Relationships in Referential Expressions with Compositional Modular Networks ...
|
|
|
|
BASE
|
|
Show details
|
|
9 |
Mapping Images to Sentiment Adjective Noun Pairs with Factorized Neural Nets ...
|
|
|
|
BASE
|
|
Show details
|
|
10 |
DeepSentiBank: Visual Sentiment Concept Classification with Deep Convolutional Neural Networks ...
|
|
|
|
BASE
|
|
Show details
|
|
12 |
Multistream Articulatory Feature-Based Models for Visual Speech Recognition
|
|
|
|
In: IEEE (2009)
|
|
BASE
|
|
Show details
|
|
|
|