AI Paper Atlas

Research map / Vision-language and multimodal / Visual question answering

Video as Conditional Graph Hierarchy for Multi-Granular Question Answering

Junbin Xiao, Angela Yao, Zhiyuan Liu, Yicong Li, Wei Ji, Tat-Seng Chua

AAAI 2022 · Vision-language and multimodal › Visual question answering · approach: Multimodal question answering datasets · 107 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 bottom object-level graph QGA G_O (ablation)HQGA · NExT-QA Valaccuracy: 50.50 -> 51.42; drops by 0.9% when removedImproved
add the bottom object-level graph QGA G_O (ablation)HQGA · MSRVTT-QA Valaccuracy: 37.26 -> 38.23; drops by 0.9% when removedImproved
add the middle-level graph QGA G_F for short-term dynamics (ablation)HQGA · NExT-QA Valaccuracy: 50.00 -> 51.42; drops over 1.2% when removedImproved
add the middle-level graph QGA G_F for short-term dynamics (ablation)HQGA · MSRVTT-QA Valaccuracy: 37.05 -> 38.23; drops over 1.2% when removedImproved
use a hierarchical graph instead of a monolithic clip-level graph (ablation)HQGA · NExT-QA Valaccuracy: 49.96 -> 51.42; drops 1.5%Improved
use a hierarchical graph instead of a monolithic clip-level graph (ablation)HQGA · MSRVTT-QA Valaccuracy: 35.66 -> 38.23; drops 2.6%Improved
use graph attention at the top level rather than sum pooling (ablation)HQGA · NExT-QA Valaccuracy: 50.74 -> 51.42; drops 0.68%Improved
use graph attention at the top level rather than sum pooling (ablation)HQGA · MSRVTT-QA Valaccuracy: 37.69 -> 38.23; drops 0.54%Improved
inject query conditioning at all levels rather than removing all query conditions (ablation)HQGA · NExT-QA Valaccuracy: 50.62 -> 51.42Improved
inject query conditioning at all levels rather than removing all query conditions (ablation)HQGA · MSRVTT-QA Valaccuracy: 37.03 -> 38.23Improved
use token-wise query conditions instead of a global query condition (ablation)HQGA · NExT-QA Valaccuracy: 50.16 -> 51.42Improved
use token-wise query conditions instead of a global query condition (ablation)HQGA · MSRVTT-QA Valaccuracy: 37.52 vs. 37.03Mixed

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