AI Paper Atlas

Research map / Video / Video segmentation and tracking

STEPs: Self-Supervised Key Step Extraction and Localization from Unlabeled Procedural Videos

Anshul Shah, Benjamin Lundell, Harpreet Sawhney, Rama Chellappa

ICCV 2023 · Video › Video segmentation and tracking · approach: Self-supervised video representation learning · 15 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 bootstrapped window (BMC2) to the contrastive loss (ablation)STEPs · MeccanoF1: 32.1 -> 33.1Improved
add multi-cue training (RGB+optical flow) (ablation)STEPs · MeccanoF1: 32.1 -> 34.2Improved
add both multi-cue training and BMC2 (ablation)STEPs · MeccanoF1: 32.1 -> 36.4Improved
add multi-cue loss and BMC2 on other egocentric sets (ablation)STEPs · EGTEA Gaze+F1: 30.8 -> 29.0No clear effect
use a transformer instead of LSTM or TCN temporal encoder (ablation)STEPs · MeccanoF1: 33.6 -> 36.4Improved
train with temporal context of 1024 chunks instead of 128 (ablation)STEPs · MeccanoF1: 33.04 -> 36.43Improved
increase training context from 1024 to 2048 chunks (ablation)STEPs · MeccanoF1: 36.43 -> 34.88Hurt
use full-video temporal extent beta=1 instead of 0.2 (ablation)STEPs · MeccanoF1: 24.7 -> 36.4Improved
add positional encoding to the input features (ablation)STEPs (BMC2) · MeccanoF1: 32.2 -> 36.4Improved
use union window for both positives and negatives (ablation)STEPs · MeccanoF1: 34.6 -> 36.4Improved
add depth as second training cue instead of gaze (ablation)STEPs · MeccanoF1: 35.4 -> 36.6Improved
use RGB+OF at inference instead of RGB aloneSTEPs · MeccanoF1: 36.4 -> 37.6Improved

Later papers that compared with this method

1 later accepted paper reports STEPS as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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