AI Paper Atlas

Research map / Video / Video-language understanding

Co-Grounding Networks With Semantic Attention for Referring Expression Comprehension in Videos

Sijie Song, Xudong Lin, Jiaying Liu, Zongming Guo, Shih-Fu Chang

CVPR 2021 · Video › Video-language understanding · approach: Temporal video grounding · 9 citations (OpenAlex)

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
replace baseline grounding with learned subject attention (ablation)One-stage LSTM baseline · VIDAcc.@0.5: 54.41 -> 58.03Improved
add learned subject and location attention (ablation)One-stage LSTM baseline · VIDAcc.@0.5: 54.41 -> 59.22Improved
use an external semantic parser instead of learned semantic attention (ablation)One-stage LSTM baseline · VIDAcc.@0.5: 54.41 -> 53.19Hurt
add co-grounding feature learning (ablation)One-stage LSTM baseline · VIDAcc.@0.5: 54.41 -> 55.88Improved
add co-grounding feature learning to subject attention (ablation)S-Att. · VIDAcc.@0.5: 58.03 -> 58.74Improved
add co-grounding feature learning to subject and location attention (ablation)SL-Att. · LiOTBAcc.@0.5: 50.51 -> 50.92Improved
add post-processing to co-grounding with semantic attention (ablation)CG-SL-Att. · VIDAcc.@0.5: 59.48 -> 60.25Improved
increase the post-processing window from P=1 to P=5 (ablation)CG-SL-Att. · VIDAcc.@0.5: 59.48 -> 60.25Improved
increase the post-processing window from P=5 to P=9 (ablation)CG-SL-Att. · VIDAcc.@0.5: 60.25 -> 59.63Hurt
apply co-grounding with the proposed framework rather than one-stage LSTMOurs · VIDAccu.@0.5: 54.78 -> 60.25Improved
apply co-grounding with the proposed framework rather than one-stage LSTMOurs · LiOTBAccu.@0.5: 49.16 -> 52.26Improved
add semantic attention to the Darknet53 baseline (ablation)SL-Att. · RefCOCO valAcc.@0.5: 73.72 -> 77.65Improved

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