AI Paper Atlas

Research map / Video / Video-language understanding

Uncovering the Temporal Context for Video Question Answering

Linchao Zhu, Zhongwen Xu, Yi Yang, Alexander G. Hauptmann

IJCV 2017 · Video › Video-language understanding · approach: Video question answering · 217 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 CCA with dual-channel ranking objectivemultiple-choice video QA · TACoS Present-Easyaccuracy: 65.1% -> 76.3%Improved
replace CCA with dual-channel ranking objectivemultiple-choice video QA · MPII-MD Present-Easyaccuracy: 41.6% -> 72.0%Improved
replace CCA with dual-channel ranking objectivemultiple-choice video QA · MEDTest 14 Present-Easyaccuracy: 63.2% -> 81.0%Improved
replace GRU with LSTM in the encoder-decoder (ablation)encoder-decoder video model · MEDTest 14 100Ex classificationaccuracy: 20.4% -> 24.9%Improved
replace averaged ConvNet features with GRU encoder-decoder featuresdual-channel ranking · TACoS Past-Easyaccuracy: 74.8% -> 78.3%Improved
replace averaged ConvNet features with GRU encoder-decoder featuresdual-channel ranking · TACoS Present-Easyaccuracy: 76.3% -> 79.7%Improved
replace averaged ConvNet features with GRU encoder-decoder featuresdual-channel ranking · TACoS Future-Easyaccuracy: 76.4% -> 78.7%Improved
replace averaged ConvNet features with GRU encoder-decoder featuresdual-channel ranking · MPII-MD Past-Easyaccuracy: 66.8% -> 72.1%Improved
replace averaged ConvNet features with GRU encoder-decoder featuresdual-channel ranking · MPII-MD Future-Easyaccuracy: 68.7% -> 73.6%Improved
replace averaged ConvNet features with GRU encoder-decoder featuresdual-channel ranking · MPII-MD Present-Hardaccuracy: 47.3% -> 48.2%Improved
add the word channel to sentence-only ranking (vary lambda) (ablation)dual-channel ranking · Present-EasyaccuracyImproved
predict future clip instead of inferring past clipGRU encoder-decoder · TACoS and MPII-MDaccuracy: Past-Easy 78.1% -> Future-Easy 76.9%Mixed

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