AI Paper Atlas

Research map / Video / Action recognition

Learning Actionness via Long-range Temporal Order Verification

Dimitri Zhukov, Jean-Baptiste Alayrac, Ivan Laptev, Josef Sivic

ECCV 2020 · Video › Action recognition · approach: Temporal action segmentation · 24 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 actionness score to inference of Zhukov et al. step localizationZhukov et al. [41] · CrossTask step localizationaverage recall (%): 22.4 -> 27.0Improved
add actionness score to inference of Miech et al. step localizationMiech et al. [23] · CrossTask step localizationaverage recall (%): 33.6 -> 34.0Improved
add actionness score to I3D HowTo100M step localizationI3D [22] · CrossTask step localizationaverage recall (%): 36.4 -> 37.6Improved
add actionness score to S3D HowTo100M step localizationS3D [22] · CrossTask step localizationaverage recall (%): 40.3 -> 41.0Improved
trim 30% of frames at start and end of training videos (ablation)order-verification actionness model · COIN and CrossTask action vs backgroundaverage precisionImproved
use long-range (minutes) instead of short-range (10-20 seconds) order verification (ablation)order-verification actionness model · COIN and CrossTask action vs backgroundaverage precisionImproved
increase number of sampled segments M above 5 (ablation)order-verification actionness model · COIN and CrossTask action vs backgroundaverage precisionHurt
sample only 3 segments instead of 5 per video (ablation)order-verification actionness model · COIN and CrossTask action vs backgroundaverage precisionHurt
use learned actionness instead of chance with trimmingactionness score · COIN action vs backgroundaverage precision (%): 53.5% -> 59.0%Improved
use learned actionness instead of chance with trimmingactionness score · CrossTask action vs backgroundaverage precision (%): 32.6% -> 47.6%Improved
add hand detector or optical flow actionness instead of chancehand detector / optical flow · COIN action vs backgroundaverage precision (%): 45.6% -> 50.6%No 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