AI Paper Atlas

Research map / Video / Video segmentation and tracking

Who's Better? Who's Best? Pairwise Deep Ranking for Skill Determination

Hazel Doughty, Dima Damen, Walterio Mayol-Cuevas

CVPR 2018 · Video › Video segmentation and tracking · approach: Self-supervised video representation learning · 161 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 a similarity loss for pairs judged comparable in skill (ablation)Siamese TSN with L_rank2 · Surgerypairwise precision (%): 69.0 -> 70.2Improved
add a similarity loss for pairs judged comparable in skill (ablation)Siamese TSN with L_rank2 · Dough-Rollingpairwise precision (%): 78.5 -> 79.4Improved
add a similarity loss for pairs judged comparable in skill (ablation)Siamese TSN with L_rank2 · Drawingpairwise precision (%): 79.1 -> 83.2Improved
add a similarity loss for pairs judged comparable in skill (ablation)Siamese TSN with L_rank2 · Chopstick-Usingpairwise precision (%): 68.8 -> 71.5Improved
add corresponding video splits to the ranking loss (ablation)Siamese TSN with L_rank1 · Drawingpairwise precision (%): 78.0 -> 79.1Improved
add corresponding video splits to the ranking loss (ablation)Siamese TSN with L_rank1 · Chopstick-Usingpairwise precision (%): 68.8 -> 68.8No clear effect
use the proposed deep ranking method instead of the strongest baselineOurs (L_rank3) · Surgerypairwise precision (%): 66.1 -> 70.2Improved
use the proposed deep ranking method instead of the strongest baselineOurs (L_rank3) · Dough-Rollingpairwise precision (%): 78.1 -> 79.4Improved
use the proposed deep ranking method instead of the strongest baselineOurs (L_rank3) · Drawingpairwise precision (%): 72.0 -> 83.2Improved
use the proposed deep ranking method instead of the strongest baselineOurs (L_rank3) · Chopstick-Usingpairwise precision (%): 76.6 -> 71.5Hurt
use the temporal stream rather than the spatial stream (ablation)Siamese TSN with L_rank3 · Surgerypairwise precision (%): 66.4 -> 72.5Improved
use the temporal stream rather than the spatial stream (ablation)Siamese TSN with L_rank3 · Dough-Rollingpairwise precision (%): 79.5 -> 79.5No 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