98 citations · 136 across the 20 of their papers we have counts for
Showing 2018Show all
2 papers · 1 filter
cs.CV2018
From Known to the Unknown: Transferring Knowledge to Answer Questions about Novel Visual and Semantic Concepts
Moshiur R Farazi, Salman H Khan, Nick Barnes
Current Visual Question Answering (VQA) systems can answer intelligent questions about `Known' visual content. However, their performance drops significantly when questions about v…
cs.CV2018★ 12 cited
Reciprocal Attention Fusion for Visual Question Answering
Moshiur R Farazi, Salman H Khan
Existing attention mechanisms either attend to local image grid or object level features for Visual Question Answering (VQA). Motivated by the observation that questions can relate…