AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

T2VLAD: Global-Local Sequence Alignment for Text-Video Retrieval

Xiaohan Wang, Linchao Zhu, Yi Yang

CVPR 2021 · Vision-language and multimodal › Cross-modal learning · approach: Probabilistic embeddings for cross-modal retrieval · 191 citations (OpenAlex)

Check 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
Use global-local alignment instead of the strongest reported baselineT2VLAD · MSRVTT 1k-A, Text → VideoR@1: 26.6 -> 29.5Improved
Use global-local alignment instead of the strongest reported baselineT2VLAD · MSRVTT 1k-B, Text → VideoR@1: 20.3 -> 26.1Improved
Use global-local alignment instead of the strongest reported baselineT2VLAD · MSRVTT Full, Text → VideoR@1: 10.0 -> 12.7Improved
Use global-local alignment instead of the strongest reported baselineT2VLAD · ActivityNet Captions, Text → VideoR@1: 22.7 -> 23.7Improved
Use global-local alignment instead of the strongest reported baselineT2VLAD · LSMDC, Video → TextR@1: 12.1 -> 14.2Improved
Add global alignment to local alignment (ablation)T2VLAD · MSRVTT 1k-A, Text → VideoR@1: 24.3 -> 29.5Improved
Add global alignment to local alignment (ablation)T2VLAD · MSRVTT 1k-A, Video → TextR@1: 26.6 -> 31.8Improved
Add local alignment to global alignment (ablation)T2VLAD · MSRVTT 1k-A, Text → VideoR@1: 22.2 -> 29.5Improved
Add local alignment to global alignment (ablation)T2VLAD · MSRVTT 1k-A, Video → TextR@1: 24.0 -> 31.8Improved
Use shared text-video VLAD rather than max pooling for video features (ablation)T2VLAD · MSRVTT 1k-A, Text → VideoR@1: 27.4 -> 29.5Improved
Use shared text-video VLAD rather than max pooling for video features (ablation)T2VLAD · MSRVTT 1k-A, Video → TextR@1: 27.5 -> 31.8Improved
Share VLAD centers across text and video (ablation)T2VLAD · MSRVTT 1k-A, Text → VideoR@1: 28.6 -> 29.5Improved

Later papers that compared with this method

1 later accepted paper reports T2VLAD as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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