AI Paper Atlas

Research map / Video / Video-language understanding

Video Question Answering with Iterative Video-Text Co-Tokenization

AJ Piergiovanni, Kairo Morton, Weicheng Kuo, Michael S. Ryoo, Anelia Angelova

ECCV 2022 · Video › Video-language understanding · approach: Video question answering · 21 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 iterative video-text co-tokenization (ablation)2-stream + Tok + MS · MSRVTT-QA (open vocab, trained from scratch)accuracy: 26.2 -> 27.6Improved
add iterative video-text co-tokenization (ablation)2-stream + Tok + MS · TGIF Frame-QA (open vocab, from scratch)accuracy: 26.2 -> 27.3Improved
add multi-scale features (ablation)2-stream + Tok · MSRVTT-QA (open vocab, trained from scratch)accuracy: 25.5 -> 26.2Improved
add learned tokenization (ablation)2-stream + Transformer · MSRVTT-QA (open vocab, trained from scratch)accuracy: 25.3 -> 25.5Improved
add transformer fusion (ablation)2-stream · MSRVTT-QA (open vocab, trained from scratch)accuracy: 24.7 -> 25.3Improved
use two streams instead of one stream (ablation)single-stream · MSRVTT-QA (open vocab, trained from scratch)accuracy: 24.8 -> 24.7No clear effect
use multiple frames instead of a single frame (ablation)video encoder · TGIF Frame-QA (open vocab, from scratch)accuracy: 24.4 -> 21.5Hurt
use masked 4k vocabulary instead of open 32k vocabulary (ablation)Ours · MSRVTT-QAaccuracy: 33.7 -> 45.7Improved
use masked vocabulary instead of FC vocabulary (ablation)Ours · MSRVTT-QAaccuracy: 42.9 -> 45.7Improved
use generative instead of contrastive pretraining on HowTo100M (ablation)single-stream X3D-M · MSRVTT-QA (single-stream X3D-M, pretraining comparison)accuracy: 26.2 -> 29.4Improved
pretrain on HowTo100M instead of YouTube8M (generative) (ablation)single-stream X3D-M · MSRVTT-QA (single-stream X3D-M, pretraining comparison)accuracy: 27.8 -> 29.4Improved
add pretraining versus random init (ablation)single-stream X3D-M · MSRVTT-QA (single-stream X3D-M, pretraining comparison)accuracy: 8.3 -> 29.4Improved

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