AI Paper Atlas

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

Learning to Answer Visual Questions From Web Videos

Antoine Yang, Antoine Miech, Josef Šivic, Ivan Laptev, Cordelia Schmid

TPAMI 2022 · Vision-language and multimodal › Visual question answering · approach: Multimodal question answering datasets · 36 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
pretrain on HowToVQA69MVQA-T · iVQA (finetuned)top-1 accuracy (%): 23.0 -> 35.4Improved
pretrain on HowToVQA69MVQA-T · MSRVTT-QA (finetuned)top-1 accuracy (%): 39.6 -> 41.5Improved
pretrain on HowToVQA69MVQA-T · How2QA (finetuned)top-1 accuracy (%): 80.8 -> 84.4Improved
pretrain on HowToVQA69M instead of HowTo100MVQA-T · iVQA (zero-shot)top-1 accuracy (%): 1.9 -> 12.2Improved
add visual modality (VQA-T vs QA-T) trained on HowToVQA69MQA-T · iVQA (zero-shot)top-1 accuracy (%): 4.4 -> 12.2Improved
use the proposed QA generation instead of Heilman et al. rule-based methodVQA-T · ActivityNet-QA (zero-shot)top-1 accuracy (%): 1.1 -> 12.2Improved
use the proposed QA generation instead of Heilman et al.VQA-T · iVQA (finetuned)top-1 accuracy (%): 31.4 -> 35.4Improved
add MLM loss together with sampling without answer repetition (ablation)VQA-T · iVQA (zero-shot)top-1 accuracy (%): 11.1 -> 12.2Improved
add MLM loss alone (without answer-repetition-free sampling) (ablation)VQA-T · iVQA (zero-shot)top-1 accuracy (%): 11.1 -> 10.9Hurt
add sampling without answer repetition (ablation)VQA-T · MSVD-QA (zero-shot)top-1 accuracy (%): 6.4 -> 7.5Improved
scale pretraining data from 1% to 100% (ablation)VQA-T · iVQA (finetuned)top-1 accuracy (%): 24.2 -> 35.4Improved
add WebVidVQA3M pretraining on top of HowToVQA69MVQA-T · MSVD-QA (finetuned)top-1 accuracy (%): 46.3 -> 47.5Improved

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