AI Paper Atlas

Research map / Video / Video-language understanding

Context-Aware Biaffine Localizing Network for Temporal Sentence Grounding

Daizong Liu, Xiaoye Qu, Jianfeng Dong, Pan Zhou, Yu Cheng, Wei Wei, Zichuan Xu, Yulai Xie

CVPR 2021 · Video › Video-language understanding · approach: Temporal video grounding · 141 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 biaffine scoring of all start-end pairs instead of boundary regression (ablation)TSG baseline · ActivityNet CaptionsR@1, IoU=0.7: 17.02 -> 22.74Improved
Use biaffine scoring of all start-end pairs instead of proposal matching (ablation)TSG baseline · ActivityNet CaptionsR@1, IoU=0.7: 20.10 -> 22.74Improved
Add MMSA to biaffine baseline (ablation)CBLN · ActivityNet CaptionsR@1, IoU=0.7: 22.74 -> 24.22Improved
Add MCBL local-global context aggregation to biaffine baseline (ablation)CBLN · ActivityNet CaptionsR@1, IoU=0.7: 22.74 -> 26.48Improved
Use local-frame concatenation instead of mean-pooling or max-pooling (ablation)CBLN MCBL · ActivityNet CaptionsR@1, IoU=0.7: 25.09 / 25.47 -> 27.60Improved
Use global max-pooling rather than sampling or mean-pooling (ablation)CBLN MCBL · ActivityNet CaptionsR@1, IoU=0.7: 24.88 / 26.02 -> 27.60Improved
Use multi-scale local windows {1,3,5} rather than a single local scale {1} (ablation)CBLN MCBL · ActivityNet CaptionsR@1, IoU=0.7: 25.45 -> 27.60Improved
Add local scale 7 to {1,3,5} (ablation)CBLN MCBL · ActivityNet CaptionsR@1, IoU=0.7: 27.60 -> 27.38Hurt
Add global scale 8 to {1,2,4} (ablation)CBLN MCBL · ActivityNet CaptionsR@1, IoU=0.7: 27.60 -> 27.72Improved
Add non-local blocks to reweight local and global contexts (ablation)CBLN MCBL · ActivityNet CaptionsR@1, IoU=0.7: 25.05 -> 27.60Improved
Use non-local blocks instead of linear layers for context interaction (ablation)CBLN MCBL · ActivityNet CaptionsR@1, IoU=0.7: 25.93 -> 27.60Improved
Use a final linear layer instead of pooling to combine local/global contexts (ablation)CBLN MCBL · ActivityNet CaptionsR@1, IoU=0.7: 26.86 -> 27.60Improved

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