AI Paper Atlas

Research map / Video / Video-language understanding

Localizing Natural Language in Videos

Jingyuan Chen, Lin Ma, Xinpeng Chen, Zequn Jie, Jiebo Luo

AAAI 2019 · Video › Video-language understanding · approach: Dense video captioning · 95 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
single-stream boundary prediction instead of sliding-window candidatesL-Net vs CTRL · TACoS/DiDeMoFPS: 562 -> 1,032Improved
add frame-specific sentence representation (ablation)L-Net · TACoS/DiDeMomIoUImproved
add cross gating (ablation)L-Net · TACoS/DiDeMomIoUImproved
add self interactor (ablation)L-Net · TACoS/DiDeMomIoUImproved
use forward/backward directional attention instead of undirected attention in self interactor (ablation)L-Net · TACoS/DiDeMomIoUImproved
L-Net vs CTRL, MCN, VSA-RNN, VSA-STVNLVL · TACoS/DiDeMoR@1, R@5Improved

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