AI Paper Atlas

Research map / Video / Video-language understanding

Multi-Speaker Video Dialog with Frame-Level Temporal Localization

Qiang Wang, Pin Jiang, Zhiyi Guo, Yahong Han, Zhou Zhao

AAAI 2020 · Video › Video-language understanding · approach: Dense video captioning · 2 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
use chat history plus video instead of chat history only (ablation)SelRef · MSVD w/o TL (20s)R@1: 17.9 -> 21.4Improved
use chat history plus video instead of video only (ablation)SelRef · MSVD w/o TL (20s)R@1: 19.5 -> 21.4Improved
use chat history plus video instead of chat history only (ablation)SelRef · MSVD-TL (50s)R@1: 17.3 -> 21.5Improved
use chat history plus video instead of video only (ablation)SelRef · MSVD-TL (50s)R@1: 19.5 -> 21.5Improved
SelRef relation modeling vs Triple EncoderSelRef (C+V) · MSVD w/o TL (20s)R@1: 18.1 -> 21.4Improved
SelRef vs TriDAF+self Attn baselineSelRef (C+V) · MSVD w/o TL (20s)R@1: 20.7 -> 21.4Improved
extend input video from 20s sub-segment to 50s fragment without temporal localizationSelRef (C+V) · MSVD w/o TLR@5: 69.7 -> 69.1Hurt
extend input video from 20s to 50s without temporal localizationTriDAF+self Attn (C+V) · MSVD w/o TLR@5: 69.4 -> 68.2Hurt
add frame-level temporal localization on 50s fragmentSelRef (C+V) · 50s fragmentR@1: 20.9 -> 21.5Improved
add temporal localization on 50s fragmentSelRef (C+V) · 50s fragmentR@5: 69.1 -> 70.1Improved
add temporal localization on 50s fragmentSelRef (V) · 50s fragmentR@1: 20.2 -> 19.5No clear effect
add temporal localization on 50s fragmentSelRef (C) · 50s fragmentR@1: 17.4 -> 17.3No clear effect

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