AI Paper Atlas

Research map / Video / Video-language understanding

Video Joint Modelling Based on Hierarchical Transformer for Co-summarization

Haopeng Li, Qiuhong Ke, Mingming Gong, Rui Zhang

TPAMI 2022 · Video › Video-language understanding · approach: Dense video captioning · 47 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
add hierarchical Transformer to the plain baseline (ablation)baseline Transformer · SumMe canonicalF-measure: 0.485 -> 0.494Improved
add frame-level video joint modelling alone to the baseline (ablation)baseline Transformer · SumMe canonicalF-measure: 0.485 -> 0.483Hurt
add Transformer-based reconstruction to the baseline (ablation)baseline Transformer · SumMe canonicalF-measure: 0.485 -> 0.488Improved
add shot-level joint modelling on top of hierarchical Transformer (ablation)VJMHT · SumMe canonicalF-measure: 0.496 -> 0.506Improved
add reconstruction on top of CS and HT (ablation)VJMHT · TVSum transferF-measure: 0.571 -> 0.583Improved
add all three components to baseline (ablation)VJMHT · TVSum transferF-measure: 0.561 -> 0.583Improved
use 2 videos rather than 1 for joint modelling (ablation)VJMHT · TVSumKendall's tau: 0.088 -> 0.097Improved
use 4 videos rather than 2 for joint modelling (ablation)VJMHT · TVSumKendall's tau: 0.097 -> 0.085Hurt
pick joint-modelling videos from the same cluster instead of random (ablation)VJMHT · TVSumKendall's tau: 0.085 -> 0.097Improved
join random or inter-cluster videos versus none (ablation)VJMHT · TVSumKendall's tau: 0.088 -> 0.085No clear effect
F-Transformer instead of C3D for frame-level modelling (ablation)VJMHT · TVSumF-measure: 0.572 -> 0.609Improved
increase shot embedding dimension from 256 to 512 (ablation)VJMHT · SumMeF-measure: 0.459 -> 0.494Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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