AI Paper Atlas

Research map / Video / Action recognition

Gait Lateral Network: Learning Discriminative and Compact Representations for Gait Recognition

Saihui Hou, Chunshui Cao, Xu Liu, Yongzhen Huang

ECCV 2020 · Video › Action recognition · approach: Skeleton-based action recognition · 240 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 lateral connections (without Compact Block) over GaitSet-L (ablation)GLN · CASIA-B CLrank-1 accuracy (%): 75.27 -> 77.22Improved
add lateral connections (without Compact Block) over GaitSet-L (ablation)GLN · CASIA-B BGrank-1 accuracy (%): 91.52 -> 91.98Improved
add Compact Block (23808-d to 256-d) (ablation)GLN · CASIA-B NMrank-1 accuracy (%): 95.58 -> 96.88Improved
add Compact Block (23808-d to 256-d) (ablation)GLN · CASIA-B BGrank-1 accuracy (%): 91.98 -> 94.04Improved
add Compact Block (23808-d to 256-d) (ablation)GLN · CASIA-B CLrank-1 accuracy (%): 77.22 -> 77.50No clear effect
add label smooth (ablation)GLN · CASIA-B NMrank-1 accuracy (%): 96.48 -> 96.88Improved
add label smooth (ablation)GLN · CASIA-B CLrank-1 accuracy (%): 77.03 -> 77.50Improved
add Lateral Pretraining before Global Training (ablation)GLN · CASIA-B BGrank-1 accuracy (%): 93.07 -> 94.04Improved
add Dropout and ReLU to Compact Block (BN+FC+BN to full) (ablation)GLN · CASIA-B CLrank-1 accuracy (%): 70.05 -> 77.50Improved
add Dropout to Compact Block (BN+ReLU+FC+BN to full) (ablation)GLN · CASIA-B CLrank-1 accuracy (%): 71.48 -> 77.50Improved
add ReLU to Compact Block (BN+Dropout+FC+BN to full) (ablation)GLN · CASIA-B CLrank-1 accuracy (%): 75.23 -> 77.50Improved
change output dimension from 128/512 to 256 (ablation)GLN · CASIA-B CLrank-1 accuracy (%): 76.84 (128), 77.10 (512), 77.50 (256)Mixed

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