AI Paper Atlas

Research map / Video / Video-language understanding

Learning from Narrated Instruction Videos

Jean-Baptiste Alayrac, Piotr Bojanowski, Nishant Agrawal, Josef Šivic, Ivan Laptev, Simon Lacoste-Julien

TPAMI 2017 · Video › Video-language understanding · approach: Event and anomaly reasoning in video · 22 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 Frank-Wolfe relaxation for multiple sequence alignment instead of Poastep discovery from narrations · Changing tire (MSA objective)objective value (lower better): 11.30 -> -5.18Improved
use Frank-Wolfe relaxation instead of Poastep discovery from narrations · Performing CPR (MSA objective)objective value (lower better): -3.82 -> -4.51Improved
use Frank-Wolfe relaxation instead of Poastep discovery from narrations · Repotting plant (MSA objective)objective value (lower better): 1.65 -> -3.55Improved
use Frank-Wolfe relaxation instead of Poastep discovery from narrations · Making coffee (MSA objective)objective value (lower better): -2.99 -> -3.86Improved
use Frank-Wolfe relaxation instead of Poastep discovery from narrations · Jumping cars (MSA objective)objective value (lower better): 4.55 -> -4.67Improved
add text narration constraints to video-only clustering (ablation)two-stage text+video clustering · Change tire and Perform CPR step localizationF1 scoreImproved
add text narration constraints to video-only clustering (ablation)two-stage text+video clustering · Make coffee step localizationF1 scoreNo clear effect
add text narration constraints to video-only clustering (ablation)two-stage text+video clustering · Jump car step localizationF1 scoreMixed
use word2vec similarity instead of WordNet in first stagetwo-stage clustering · step localizationF1 scoreNo clear effect
tune regularization lambda away from 1/(N K_pred)two-stage clustering · five tasks averageF1 score: up to 5% improvement from a good choice of lambdaMixed
use very large caption delays (Delta b, Delta a) > (60, 60)two-stage clustering · five tasks averageF1 score: drop of more than 5%Hurt
add localization noise to narration constraints (ablation)two-stage clustering · five tasks averageF1 scoreNo 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