FiLM: Visual Reasoning with a General Conditioning Layer
Open paper
Benchmark
Model
Rank
Results
visual-question-answering-on-clevr
CNN+GRU+FiLM
#10
Accuracy: 97.7
visual-question-answering-on-clevr-humans
CNN+GRU+FiLM
#3
Accuracy: 75.9
Rank counts only results with a code link.