AI Paper Atlas

Research map / Video / Action recognition

VSViG: Real-time Video-based Seizure Detection via Skeleton-based Spatiotemporal ViG

Yankun Xu, Junzhe Wang, Yun-Hsuan Chen, Jie Yang, Wenjie Ming, Shuang Wang, Mohamad Sawan

ECCV 2024 · Video › Action recognition · approach: Fully supervised temporal action detection · 11 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 both inter-partition and intra-partition spatial modules (ablation)VSViG · patient video validationRMSE: 13.0 -> 5.9Improved
add intra-partition module on top of inter-only (ablation)VSViG · patient video validationRMSE: 11.7 -> 5.9Improved
use K_S=3 spatial neighbors in temporal convolution instead of K_S=1 (ablation)VSViG · patient video validationRMSE: 9.9 -> 5.9Improved
use temporal kernel K_T=5 instead of 3 (ablation)VSViG · patient video validationRMSE: 5.9 -> 6.5Hurt
add dynamic partition (shuffle partitions before temporal update) (ablation)VSViG · patient video validationRMSE: 8.4 -> 5.9Improved
add Stem(x, y) positional embedding (ablation)VSViG · patient video validationRMSE: 9.1 -> 5.9Improved
use Gaussian sigma 0.3 rather than 0.1 for patch extraction (ablation)VSViG · patient video validationRMSE: 10.1 -> 5.9Improved
use exponential rather than linear transition-period labels (ablation)VSViG · patient video validationRMSE: 6.7% -> 5.9%Improved
add accumulative probability decision rule (ablation)VSViG · seizure onset detection DT=0.3latency after EEG onset: 11.4s -> 5.1sImproved
use skeleton-based skeleton models instead of RGB-based modelsseizure detection baselines · patient video validationRMSE (%): R3D+ViT 14.2 -> HDGCN 7.9Improved
use skeleton-based patch embeddings instead of coordinates (VSViG vs best GCN)skeleton action recognition · patient video validationRMSE (%): 7.9 -> 5.9Improved

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