AI Paper Atlas

Research map / 3D vision / Face and shape

Coding Kendall's Shape Trajectories for 3D Action Recognition

Amor Ben Tanfous, Hassen Drira, Boulbaba Ben Amor

CVPR 2018 · 3D vision › Face and shape · approach: Primitive-based shape abstraction · 63 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 class-specific dictionaries instead of a global dictionary (ablation)Kendall sparse coding with Bi-LSTM · Florence3D-Action, LOAOaccuracy: 91.53% -> 94.48%Improved
use a global dictionary instead of class-specific dictionaries (ablation)Kendall sparse coding with Bi-LSTM · Florence3D-Action, LOAOaccuracy: 94.48% -> 91.53%Hurt
use bidirectional LSTM instead of traditional LSTM (ablation)Kendall sparse-code trajectories · Florence3D-Action, LOAOaccuracy: around 0.7%Improved
initialize the dictionary with Bayesian shape clustering and PGA rather than random training shapes (ablation)Kendall dictionary learning · Florence3D-Action, tight lace classdictionary learning convergence speed: approximately two timesImproved
increase sparsity regularization to λ = 0.01 (ablation)Kendall sparse coding with FTP-SVM · Florence3D-Action validation splitaccuracy: 37% of sparsityImproved
increase sparsity regularization to λ = 0.02 (ablation)Kendall sparse coding with Bi-LSTM · Florence3D-Action validation splitaccuracy: 49% of sparsityImproved
use Kendall sparse-code functions with FTP-SVM instead of the compared Riemannian representation3D action recognition · MSR-Action 3D, protocol [28]accuracy: 92.46 -> 94.19Improved
use Kendall sparse-code functions with FTP-SVM instead of the compared Riemannian representation3D action recognition · Florence3D-Action, protocol [38]accuracy: 90.8 -> 92.85Improved
use Kendall sparse-code functions with Bi-LSTM instead of the compared Riemannian representation3D action recognition · UTKinect-Action, protocol [38]accuracy: 97.08 -> 96.89Hurt
use Kendall sparse-code functions with FTP-SVM instead of the compared Riemannian representation3D action recognition · UTKinect-Action, protocol [38]accuracy: 97.08 -> 97.39Improved
use Bi-LSTM without an additional noise-processing step instead of FTP-SVMKendall sparse-code trajectories · MSR-Action 3D, protocol [28]accuracy: 94.19 -> 91.84Hurt

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