AI Paper Atlas

Research map / 3D vision / Human pose estimation

Chained Predictions Using Convolutional Neural Networks

Georgia Gkioxari, Alexander Toshev, Navdeep Jaitly

ECCV 2016 · 3D vision › Human pose estimation · approach: Heatmap and coordinate pose encoding · 195 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 chained predictions (condition on previous joints) vs same-depth feedforward (ablation)24-layer CNN · MPII valPCKh mean (%): 75.6 -> 79.6Improved
add chained predictions to base network (ablation)Inception-v3 encoder · MPII valPCKh mean (%): 81.3 -> 85.3Improved
use multi-scale deception instead of single deconvolution (ablation)6-layer base network · MPII valPCKh mean (%): 72.6 -> 73.9Improved
add multi-crop evaluationChain Model · MPII valPCKh mean (%): 79.6 -> 82.2Improved
feed ground-truth previous joints (oracle) (ablation)Chain Model · MPII valPCKh mean (%): 79.6 -> 85.9Improved
use inception-v3 encoder instead of shallow 6-layer encoderBase Network · MPII valPCKh mean (%): 73.9 -> 81.3Improved
add chained predictions to base network (ablation)6-layer CNN · MPII val, wristPCKh (%): 69.0 -> 74.6Improved
add chaining in time (T_H=3) vs per-frame base network (ablation)Base Network · Penn Action testPCK mean (%): 87.5 -> 91.7Improved
connect previous outputs to hidden state (chain model vs plain conv RNN) (ablation)convolutional RNN · Penn Action testPCK mean (%): 90.1 -> 91.7Improved
increase time horizon from 1 to 3 (ablation)Chain Model · Penn Action testPCK mean (%): 91.0 -> 91.7Improved
add temporal smoothing with ViterbiBase Network · Penn Action testPCK mean (%): 87.5 -> 88.6Improved
add chaining in joints in addition to time (ablation)Chain Model T_H=3 · Penn Action testPCK mean (%): 91.7 -> 91.8No 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