AI Paper Atlas

Research map / Video / Action recognition

SportsCap: Monocular 3D Human Motion Capture and Fine-Grained Understanding in Challenging Sports Videos

Xin Chen, Anqi Pang, Wei H. Yang, Yuexin Ma, Lan Xu, Jingyi Yu A

IJCV 2021 · Video › Action recognition · approach: Temporal action segmentation · 69 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 prior loss from sports pose embedding space (ablation)Motion Embedding Module · SMARTPCK-0.3: 70.9 -> 83.6Improved
use semantic (per sub-motion) rather than general pose space (ablation)Motion Embedding Module · SMARTPCK-0.3: 83.0 -> 84.8Improved
use semantic (per sub-motion) rather than general pose space (ablation)Motion Embedding Module · SMARTPCK-0.5: 92.1 -> 92.4Improved
add multi-task learning with action parsing module (ablation)Motion Embedding Module (ResNet152) · SMARTPCK-0.5: 94.8 -> 96.0Improved
deeper backbone ResNet50 to ResNet101 (ablation)Motion Embedding Module · SMARTPCK-0.3: 84.8 -> 87.5Improved
deeper backbone ResNet101 to ResNet152 (ablation)Motion Embedding Module · SMARTPCK-0.3: 87.5 -> 88.5Improved
add pose-coefficient P-stream to joint and bone streams with SAMB (ablation)Action Parsing Module · SMART diving numberTop-1 accuracy: 67.1 -> 82.2Improved
add bone stream to joint stream (ablation)Action Parsing Module · SMART diving numberTop-1 accuracy: 65.0 -> 67.1Improved
use Semantic Attributes Mapping Block instead of black-box (ablation)Action Parsing Module · SMART diving numberTop-1 accuracy: 78.0 -> 82.2Improved
add SAMB to speed convergence (ablation)Action Parsing Module · SMARTepochs to converge: 70 -> 50 -> 10Improved
use SportsCap instead of ST-GCNAction parsing · FineGym partial Gym288mean accuracy: 11.0 -> 46.9Improved
use SportsCap instead of C3D-AVGAction parsing · AQATwist No. / Some No.: 97.5 -> 97.9 / 96.9 -> 96.3Mixed

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