AI Paper Atlas

Research map / Video / Video-language understanding

Saying the Unseen: Video Descriptions via Dialog Agents

Ye Zhu, Yu Wu, Yi Yang, Yan Yan

TPAMI 2021 · Video › Video-language understanding · approach: Video question answering

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 dialog between agents instead of no dialogQ-BOT MM · AVSDCIDEr: 14.2 -> 22.1Improved
use discriminative instead of generative internal dialogQA-C · AVSDCIDEr: 22.9 -> 27.1Improved
add attention modules (ablation)QA-C(G) · AVSDCIDEr: 20.4 -> 22.9Improved
add attention modules (ablation)QA-C(D) · AVSDCIDEr: 25.3 -> 27.1Improved
add audio-visual LSTM (ablation)QA-C(G) · AVSDCIDEr: +2.6Improved
add audio-visual LSTM (ablation)QA-C(D) · AVSDCIDEr: +3.4Improved
add internal selective mechanism with sparse annotations (ablation)QA-C(D) · AVSDCIDEr: 26.3 -> 27.1Improved
use MM attention instead of IM attentionQA-C(D) · AVSDCIDEr: 26.1 -> 27.1Improved
keep QA pair order instead of shuffling (ablation)QA-C(G) · AVSDCIDEr: -2.9Improved
keep QA pair order instead of shuffling (ablation)QA-C(D) · AVSDCIDEr: -1.7Improved
add audio input for A-BOT (ablation)QA-C(D) · AVSDCIDEr: 26.6 -> 27.1Improved
add input descriptions for A-BOT (ablation)QA-C(G) · AVSDCIDEr: 20.1 -> 22.9Improved

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