AI Paper Atlas

Research map / 3D vision / Human pose estimation

Human Motion Analysis with Deep Metric Learning

Huseyin Coskun, David Joseph Tan, Sailesh Conjeti, Nassir Navab, Federico Tombari

ECCV 2018 · 3D vision › Human pose estimation · approach: Human motion prediction · 56 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 self-attention (ablation)MMD-NCA · CMU mocap action recognition (unseen categories)FPR at 70% TPR: 30.04 -> 20.29Improved
add self-attention (ablation)MMD-NCA · Human3.6M action recognition (unseen categories)FPR at 70% TPR: 41.01 -> 33.13Improved
add self-attention (ablation)MMD-NCA · CMU mocap person identificationFPR at 70% TPR: 16.78 -> 2.55Improved
add layer normalization to the LSTM (ablation)MMD-NCA · CMU mocap action recognition (unseen categories)FPR at 70% TPR: 27.95 -> 20.29Improved
add layer normalization to the LSTM (ablation)MMD-NCA · Human3.6M action recognition (unseen categories)FPR at 70% TPR: 38.09 -> 33.13Improved
add layer normalization to the LSTM (ablation)MMD-NCA · CMU mocap person identificationFPR at 70% TPR: 7.36 -> 2.55Improved
use Gaussian mixture kernel instead of linear kernel in MMD (ablation)MMD-NCA · CMU mocap action recognition (unseen categories)FPR at 70% TPR: 29.00 -> 20.29Improved
use Gaussian mixture kernel instead of polynomial kernel in MMD (ablation)MMD-NCA · CMU mocap person identificationFPR at 70% TPR: 5.93 -> 2.55Improved
use Gaussian mixture kernel instead of linear kernel in MMD (ablation)MMD-NCA · CMU mocap person identificationFPR at 95% TPR: 35.75 -> 19.31Improved
use MMD-NCA loss instead of triplet lossattentive BiLSTM · CMU mocap action recognition (unseen categories)FPR at 70% TPR: 28.77 -> 20.29Improved
use MMD-NCA loss instead of N-Pair lossattentive BiLSTM · Human3.6M action recognition (unseen categories)FPR at 70% TPR: 36.52 -> 33.13Improved
use MMD-NCA loss instead of N-Pair lossattentive BiLSTM · CMU mocap person identificationFPR at 70% TPR: 4.56 -> 2.55Improved

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