AI Paper Atlas

Research map / Video / Video-language understanding

Unifying Event Detection and Captioning as Sequence Generation via Pre-training

Qi Zhang, Yuqing Song, Qin Jin

ECCV 2022 · Video › Video-language understanding · approach: Dense video captioning · 28 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 MLM pre-training (ablation)captioning model w/o pre-training · ActivityNet Captions val (GT events, ablation)CIDEr: 47.7 -> 49.05Improved
add MLM pre-training (ablation)captioning model w/o pre-training · ActivityNet Captions val (GT events, ablation)BLEU@4: 2.22 -> 2.17Hurt
add MVFR pre-training on top of MLM (ablation)captioning model · ActivityNet Captions val (GT events, ablation)CIDEr: 49.05 -> 51.08Improved
add MEFM pre-training (ablation)captioning model with MLM+MVFR · ActivityNet Captions val (GT events, ablation)CIDEr: 51.08 -> 52.13Improved
add MEFM pre-training (ablation)captioning model with MLM+MVFR · ActivityNet Captions val (GT events, ablation)BLEU@4: 2.38 -> 2.59Improved
add semantic concept (CPT) features (ablation)captioning model · ActivityNet Captions val (GT events, ablation)CIDEr: 52.13 -> 52.42Improved
add MEFM pre-training (ablation)detection model w/o pre-training · ActivityNet Captions val (event detection, ablation)average recall: 54.94 -> 56.49Improved
add MLM pre-training (ablation)detection model with MEFM · ActivityNet Captions val (event detection, ablation)average recall: 56.49 -> 58.00Improved
add MVFR pre-training (ablation)detection model with MEFM+MLM · ActivityNet Captions val (event detection, ablation)average recall: 58.00 -> 58.32Improved
add MLM and MVFR tasks (ablation)detection model with MEFM · ActivityNet Captions val (event detection, ablation)average precision: 58.12 -> 59.95Improved
add semantic concept (CPT) features (ablation)detection model · ActivityNet Captions val (event detection, ablation)average recall: 58.32 -> 59.00Improved
add semantic concept (CPT) features (ablation)detection model · ActivityNet Captions val (event detection, ablation)average precision: 59.95 -> 60.32Improved

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