Unifying the Video and Question Attentions for Open-Ended Video Question Answering

67 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

NExT-QA: Next Phase of Question-Answering to Explaining Temporal Actions (2021, methodology): “For better comparison, we also reproduce UATT [53] which was proposed for generation-based open-ended QA by designing an order-preserved co-attention module.”
Spatiotemporal-Textual Co-Attention Network for Video Question Answering (2019, background): “Moreover, these works [6, 50] only learn appearance representation without the exploration of motion patterns in videos.”
Open-Ended Video Question Answering via Multi-Modal Conditional Adversarial Networks (2020, methodology): “• Unified method [2] is the co-attention reasoning network, which applied the attention mechanism on videos and questions to generate the natural language answer.”
Multichannel Attention Refinement for Video Question Answering (2020, background): “Reference Reference [50] proposed to integrate both the sequential video attention and the temporal question attention to update features encoded by bi-directional LSTMs.”