Search Results for author:
Found 3 papers, 0 papers with code
Learning Compositional Representation for Few-shot Visual Question Answering
Experimental results on the VQA v2. 0 validation dataset demonstrate the effectiveness of our proposed attribute network and the constraint between answers and their corresponding attributes, as well as the ability of our method to handle the answers with few training examples.
Bilinear Graph Networks for Visual Question Answering
The question-graph exchanges information between these output nodes from image-graph to amplify the implicit yet important relationship between objects.
Ranked #16 on
Visual Question Answering (VQA)
on VQA v2 test-std
Image-Question-Answer Synergistic Network for Visual Dialog
Afterward, in the second stage, answers with high probability of being correct are re-ranked by synergizing with image and question.
Ranked #57 on
Visual Dialog
on Visual Dialog v1.0 test-std
