AI Paper Atlas

Research map / Video / Video-language understanding

Multi-Event Video-Text Retrieval

Gengyuan Zhang, Jisen Ren, Jindong Gu, Volker Tresp

ICCV 2023 · Video › Video-language understanding · approach: Text-video retrieval · 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 key event selection (K-Medoids frames) (ablation)Me-Retriever · ActivityNet Captions Video-to-TextRecall@1-Average: 7.40 -> 8.52Improved
add MeVTR loss instead of cross-entropy (ablation)Me-Retriever · ActivityNet Captions Video-to-TextRecall@1-Average: 6.70 -> 8.52Improved
add key event selection (ablation)Me-Retriever · ActivityNet Captions Text-to-VideoRecall@1: 15.03 -> 15.17Improved
add MeVTR loss instead of cross-entropy (ablation)Me-Retriever · ActivityNet Captions Text-to-VideoRecall@1: 14.45 -> 15.17Improved
use dynamic weight alpha instead of fixed alpha (ablation)MeVTR loss · ActivityNet Captions Video-to-Text and Text-to-VideoRecall@5Improved
increase fixed alpha beyond 1.0-2.0 (ablation)MeVTR loss · ActivityNet CaptionsRecall@5Mixed
use max instead of avg key-event similarity (ablation)Me-Retriever · Charades-Event Text-to-VideoRecall@1: 1.88 -> 2.02Improved
use max instead of avg key-event similarity (ablation)Me-Retriever · ActivityNet Captions Text-to-VideoRecall@1: 15.99 -> 14.93Hurt
use max instead of avg key-event similarity (ablation)Me-Retriever · ActivityNet Captions Video-to-TextRecall@1-Average: 8.52 -> 6.98Hurt
use Me-Retriever(avg) instead of CLIP4Clip(mean) (ablation)video encoder aggregation · ActivityNet Captions Video-to-TextRecall@1-Average: 6.60 -> 8.52Improved
use Me-Retriever(avg) instead of CLIP4Clip(mean) (ablation)video encoder aggregation · ActivityNet Captions Text-to-VideoRecall@1: 15.25 -> 15.99No clear effect
use Me-Retriever(avg) instead of CLIP4Clip(mean)video encoder aggregation · Charades-Event Video-to-TextRecall@1-Average: 1.32 -> 1.39Improved

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