AI Paper Atlas

Research map / Video / Video-language understanding

On the Hidden Treasure of Dialog in Video Question Answering

Deniz Engin, François Schnitzler, Ngoc Q. K. Duong, Yannis Avrithis

ICCV 2021 · Video › Video-language understanding · approach: Video question answering · 15 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace human plot with generated episode dialog summary (ablation)ROLL pipeline · KnowIT VQA testaccuracy (overall): 0.724 -> 0.775Improved
add scene dialog summary in place of dialog stream (ablation)multi-stream QA · KnowIT VQA testaccuracy (overall): 0.775 -> 0.781Improved
add temporal attention (ablation)ROLL pipeline · KnowIT VQA testaccuracy (overall): 0.715 -> 0.724Improved
increase plot parts from 5 to 10 (ablation)ROLL pipeline · KnowIT VQA testaccuracy (overall): 0.703 -> 0.714Improved
change BERT argument order for episode inputs (ablation)ROLL pipeline · KnowIT VQA testaccuracy (overall): 0.714 -> 0.715No clear effect
replace modality weighting with multi-stream attention (ablation)ROLL pipeline · KnowIT VQA testaccuracy (overall): 0.704 -> 0.703No clear effect
add soft temporal attention to episode dialog summary single-stream (ablation)single-stream QA · KnowIT VQA test (single-stream)accuracy (overall): 0.723 -> 0.756Improved
add soft temporal attention to plot single-stream (ablation)single-stream QA · KnowIT VQA test (single-stream)accuracy (overall): 0.683 -> 0.702Improved
add soft temporal attention in single-stream for multi-stream V+S+E (ablation)multi-stream attention · KnowIT VQA testaccuracy (overall): 0.711 -> 0.781Improved
use multi-stream attention instead of product fusion (ablation)fusion V+S+E · KnowIT VQA testaccuracy (overall): 0.739 -> 0.781Improved
add self-attention to multi-stream attention (ablation)multi-stream attention · KnowIT VQA testaccuracy (overall): 0.781 -> 0.770Hurt
use learned multi-stream attention instead of oracle question-type attention (ablation)multi-stream attention · KnowIT VQA testaccuracy (overall): 0.745 -> 0.781Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy