AI Paper Atlas

Research map / Video / Action recognition

Video-Mined Task Graphs for Keystep Recognition in Instructional Videos

Kumar Ashutosh, Santhosh Kumar Ramakrishnan, Triantafyllos Afouras, Kristen Grauman

NeurIPS 2023 · Video › Action recognition · approach: Action anticipation and latent actions · 10 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 probabilistic task graph instead of non-probabilistic (ablation)PathSearch keystep assignment · COIN text-onlyaccuracy (%): 10.5 -> 16.3Improved
use fixed confidence threshold instead of adaptive per-video threshold (ablation)PathSearch · COIN text-onlyaccuracy (%): 12.5 -> 16.3Improved
use fixed threshold instead of adaptive (ablation)PathSearch · CrossTask text-onlyaccuracy (%): 17.1 -> 20.0Improved
use PathSearch (beam search) instead of Bayesian recursive filtering (ablation)keystep assignment · COIN text-onlyaccuracy (%): 13.5 -> 16.3Improved
prioritize video keysteps over fusion for video-text (ablation)keystep assignment · COIN video-textaccuracy (%): 14.0 -> 16.9Improved
lower text threshold gamma from 0.5 to 0.3 (ablation)PathSearch · COIN text-onlyaccuracy (%): 16.3 -> 15.9Hurt
raise video threshold gamma from 0.3 to 0.5 (ablation)PathSearch · COIN video-onlyaccuracy (%): 15.4 -> 14.9Hurt
add video-mined task graph to similarity baselineOurs vs VideoCLIP · CrossTask video-onlyaccuracy (%): 28.5 -> 28.6No clear effect
add task graph under low keystep predictability (ablation)Ours vs DistantSup. · COIN text-onlyaccuracy (%): 8.3 -> 14.1Improved
increase vocabulary with noisy keysteps to 10 x NOurs vs DistantSup. · COIN text-onlyaccuracy (%): 4.3 -> 8.4Improved

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