AI Paper Atlas

Research map / Video / Video-language understanding

Dual Encoding for Video Retrieval by Text

Jianfeng Dong, Xirong Li, Chaoxi Xu, Xun Yang, Gang Yang, Xun Wang, Meng Wang

TPAMI 2021 · Video › Video-language understanding · approach: Text-video retrieval · 220 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 biGRU-CNN level to mean pooling and biGRU (all three levels) (ablation)Dual Encoding · MSR-VTT officialSumR: 203.8 -> 211.7Improved
add level 2 (biGRU) to level 1 (mean pooling) (ablation)Dual Encoding · MSR-VTT officialSumR: 182.9 -> 195.3Improved
use biGRU-CNN instead of mean pooling as single encoder (ablation)Dual Encoding · MSR-VTT officialSumR: 182.9 -> 197.9Improved
add text-side multi-level encoding to video-side multi-level encoding (ablation)Dual Encoding · MSR-VTT officialSumR: 194.5 -> 211.7Improved
add video-side multi-level encoding to text-side multi-level encoding (ablation)Dual Encoding · MSR-VTT officialSumR: 191 -> 211.7Improved
use hybrid space instead of latent space only (ablation)Dual Encoding · MSR-VTT officialSumR: 199.0 -> 211.7Improved
use hybrid space instead of concept space only (ablation)Dual Encoding · MSR-VTT officialSumR: 187.4 -> 211.7Improved
increase latent space dimension from 1,536 to 2,048 (ablation)Dual Encoding · MSR-VTT officialSumR: 199.0 -> 197.7No clear effect
add triplet ranking loss for concept space learning (ablation)Dual Encoding · MSR-VTT officialSumR: 183.3 -> 211.7Improved
add pre-trained Transformer features (MMT, BERT)Dual Encoding · MSR-VTT Test1k-Yutext-to-video R@1: 21.1 -> 32.4Improved
use Transformer features only instead of multi-level encoding (ablation)Dual Encoding · MSR-VTT officialtext-to-video R@1: 11.6 -> 8.5Hurt
add multi-level text encoding to VSE++VSE++ · Flickr30kSumR: 291.3 -> 310.7Improved

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