AI Paper Atlas

Research map / Video / Video-language understanding

Video Graph Transformer for Video Question Answering

Junbin Xiao, Pan Zhou, Tat-Seng Chua, Shuicheng Yan

ECCV 2022 · Video › Video-language understanding · approach: Video question answering · 110 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
add the dynamic graph transformer module (ablation)VGT · NExT-QA valAcc@All: 53.22 -> 55.02Improved
add the dynamic graph transformer module (ablation)VGT · TGIF-QA Actionaccuracy: 89.6 -> 95.0Improved
add temporal graph transformer (node and edge) (ablation)VGT · NExT-QA valAcc@All: 53.74 -> 55.02Improved
add node transformer (ablation)VGT · NExT-QA valAcc@All: 53.84 -> 55.02Improved
add edge transformer (ablation)VGT · NExT-QA valAcc@All: 54.30 -> 55.02Improved
add global frame feature F_I (ablation)VGT · NExT-QA valAcc@All: 53.58 -> 55.02Improved
use similarity comparison instead of answer classification (ablation)VGT · NExT-QA valAcc@All: 45.82 -> 55.02Improved
use similarity comparison instead of answer classification (ablation)VGT · FrameQAaccuracy: 56.9 -> 61.6Improved
replace cross-modal transformer with light cross-modal interaction in classification variant (ablation)Comp->CLS · NExT-QA valAcc@All: 45.82 -> 46.98No clear effect
replace S3D with DGT encoder in VQA-T (ablation)VQA-T · NExT-QA valAcc@All: 45.30 -> 50.02Improved
replace cross-modal transformer with cross-modal interaction module in VQA-T (ablation)VQA-T · NExT-QA valAcc@All: 45.30 -> 45.40No clear effect
add cross-modal interaction (ablation)VGT · TGIF-QAaccuracy: more than 10%Improved

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