AI Paper Atlas

Research map / Video / Video-language understanding

Bidirectional Attentive Fusion With Context Gating for Dense Video Captioning

Jingwen Wang, Wenhao Jiang, Lin Ma, Wei Liu, Yong Xu

CVPR 2018 · Video › Video-language understanding · approach: Dense video captioning · 224 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
combine forward and backward proposal predictions to use past and future contextSST proposals · ActivityNet CaptionsF1@1000: 0.566 -> 0.602Improved
combine forward and backward proposal predictions to use past and future contextSST proposals · THUMOS-14Recall@10: 0.053 -> 0.063Improved
add bidirectional proposal predictionsSST proposals · THUMOS-14, tIoU=0.8Recall@1000: 0.696 -> 0.711Improved
use bidirectional rather than forward-only proposal context (ablation)ActivityNet Captions captioning · ActivityNet Captions validation, top 1000 proposalsMeteor: 7.87 -> 8.35Improved
add event clip features to context vectors (ablation)Bi-SST captioning · ActivityNet Captions validation, top 1000 proposalsMeteor: 8.35 -> 8.78Improved
add context vectors to event clip features (ablation)Bi-SST captioning · ActivityNet Captions validation, top 1000 proposalsMeteor: 8.36 -> 8.78Improved
use temporal dynamic attention instead of mean pooling (ablation)Bi-SST + E + H · ActivityNet Captions validation, top 1000 proposalsMeteor: 8.78 -> 9.00Improved
add context gating to balance event features and context (ablation)Bi-SST + E + H + TDA · ActivityNet Captions validation, top 1000 proposalsMeteor: 9.00 -> 9.19Improved
add joint proposal-caption ranking at inference (ablation)Bi-SST + E + H + TDA + CG · ActivityNet Captions validation, top 1000 proposalsMeteor: 9.19 -> 9.60Improved
use the complete proposed system rather than the prior state-of-the-art methodDense video captioning · ActivityNet Captions testMeteor: 4.82 -> 9.65Improved

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