AI Paper Atlas

Research map / 3D vision / Human pose estimation

SeqHAND: RGB-Sequence-Based 3D Hand Pose and Shape Estimation

John Yang, Hyung Jin Chang, Seungeui Lee, Nojun Kwak

ECCV 2020 · 3D vision › Human pose estimation · approach: Depth-based hand pose regression · 51 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 ConvLSTM layer to the ResNet-50 encoder (ablation)ResNet50 encoder · SeqHAND validation3D error (mm): 7.85 -> 7.18Improved
add a plain LSTM layer to the ResNet-50 encoder (ablation)ResNet50 encoder · SeqHAND validation3D error (mm): 7.85 -> 9.63Hurt
replace encoder with I3D 3D convolution (ablation)ResNet50 encoder · SeqHAND validation3D error (mm): 7.85 -> 9.24Hurt
replace encoder with MFNet motion-feature network (ablation)ResNet50 encoder · SeqHAND validation3D error (mm): 7.85 -> 10.54Hurt
use ResNet101 instead of ResNet50 backbone (ablation)encoder baseline · SeqHAND validation3D error (mm): 7.85 -> 7.54Improved
detach ConvLSTM from real-domain finetuning (ablation)SeqHAND-Net · EgoDexter (ED)avg 3D error (mm): 40.94 -> 17.16Improved
detach ConvLSTM from real-domain finetuning (ablation)SeqHAND-Net · Dexter+Object (DO)avg 3D error (mm): 29.41 -> 18.12Improved
detach ConvLSTM from real-domain finetuning (ablation)SeqHAND-Net · STBavg 3D error (mm): 9.82 -> 9.87No clear effect
add SeqHAND sequential pretraining with ConvLSTM, then finetune with ConvLSTM also finetuned (vs non-sequential synthetic pretraining) (ablation)encoder · EgoDexter (ED)avg 3D error (mm): 49.18 -> 40.94Improved
add SeqHAND sequential pretraining with ConvLSTM, then finetune with ConvLSTM also finetuned (vs non-sequential synthetic pretraining) (ablation)encoder · Dexter+Object (DO)avg 3D error (mm): 33.12 -> 29.41Improved
add SeqHAND sequential pretraining with ConvLSTM, finetuned jointly (vs non-sequential synthetic pretraining) (ablation)encoder · STBavg 3D error (mm): 9.80 -> 9.82No clear effect
finetune on FreiHand+STB after synthetic pretraining (ablation)encoder (no ConvLSTM) · Dexter+Object (DO)avg 3D error (mm): 100.84 -> 33.12Improved

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