AI Paper Atlas

Research map / Video / Video-language understanding

Learning to Localize Actions in Instructional Videos with LLM-Based Multi-Pathway Text-Video Alignment

Yuxiao Chen, Kai Li, Wentao Bao, Deep Patel, Yu Kong, Martin Renqiang Min, Dimitris N. Metaxas

ECCV 2024 · Video › Video-language understanding · approach: Video-language pretraining · 8 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
train on LLM-steps instead of wikiHow-steps plus narrations (ablation)MPTVA training · HT-StepR@1: 35.9 -> 41.9Improved
add narrations to LLM-steps training (ablation)MPTVA training · HT-StepR@1: 41.9 -> 43.3Improved
use MPTVA pseudo-labels instead of timestamp labels for narrations (ablation)narration training · HT-StepR@1: 30.3 -> 32.1Improved
use narrations instead of wikiHow-steps with the same MPTVA supervision (ablation)MPTVA training · HT-StepR@1: 31.2 -> 32.1Improved
fuse all three alignment pathways rather than best single pathway (S-V-Short) (ablation)MPTVA · HT-StepR@1: 37.7 -> 41.9Improved
fuse all three pathways rather than best single pathway on CrossTask (ablation)MPTVA · CrossTaskAvg. R@1: 41.6 -> 47.0Improved
add S-V-Short pathway to S-V-Long + S-N-V (ablation)MPTVA · HT-StepR@1: 37.9 -> 41.9Improved
train on S-N-V timestamp-derived labels instead of direct video alignment labels (ablation)MPTVA · HT-StepR@1: 34.2 vs 37.7 (S-V-Short)Hurt
raise pseudo-label filter threshold from 0.65 to 0.70 (ablation)MPTVA pseudo-labels · HT-StepR@1: 40.6 -> 35.4Hurt
lower filter threshold from 0.65 to 0.60 (ablation)MPTVA pseudo-labels · HT-StepR@1: 40.6 -> 39.2Hurt
increase pseudo-label window size from 2 to 5 (ablation)MPTVA pseudo-labels · HT-StepR@1: 41.9 -> 40.6Hurt
decrease window size from 2 to 1 (ablation)MPTVA pseudo-labels · HT-StepR@1: 41.9 -> 40.3Hurt

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