AI Paper Atlas

Research map / Video / Action recognition

PosMLP-Video: Spatial and Temporal Relative Position Encoding for Efficient Video Recognition

Yanbin Hao, Diansong Zhou, Zhicai Wang, Chong‐Wah Ngo, Xiangnan He, Meng Wang

IJCV 2024 · Video › Action recognition · approach: Contrastive video representation learning · 10 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
combine PoTGU and PoSGU in parallel instead of PoSGU alone (ablation)PosMLP-Video-S · Something-Something V1 (no pretraining)Top-1 accuracy (%): 6.25 -> 46.31Improved
add temporal gating (PoTGU) in place of spatial-only PoSGU (ablation)PosMLP-Video-S · Something-Something V1 (no pretraining)Top-1 accuracy (%): 6.25 -> 25.44Improved
use joint PoSTGU instead of factorized PoTGU+PoSGU (ablation)PosMLP-Video-S · Something-Something V1 (no pretraining)Top-1 / GFLOPs: 40.89 vs 46.31; 103.09 vs 40.49 GFLOPsMixed
parallel PoTGU+PoSGU instead of cascaded PoTGU->PoSGU (ablation)PosMLP-Video-S · Something-Something V1 (no pretraining)Top-1 accuracy (%): 44.11 -> 46.31Improved
pretrain on ImageNet-1K (ablation)PosMLP-Video-S · Something-Something V1Top-1 accuracy (%): 46.31 -> 52.24Improved
use positional units instead of gMLP SGU+TGU (ablation)PosMLP-Video-S · Something-Something V1 (no pretraining)Top-1 accuracy (%): 42.94 -> 46.31Improved
use PoSGU instead of temporal convolution+PoSGU (TConv) (ablation)PosMLP-Video-S · Something-Something V1 (no pretraining)Top-1 accuracy (%): 42.25 -> 46.31Improved
use temporal window 16 instead of 8 (ablation)PosMLP-Video-S · Something-Something V1 (no pretraining)Top-1 accuracy (%): 40.73 -> 46.31Improved
enlarge spatial window in stage 1 to 28x28 (ablation)PosMLP-Video-S · Something-Something V1 (no pretraining)Top-1 accuracy (%): 46.31 -> 46.29No clear effect
use group number g=(8,16,32,64) instead of g=(1,1,1,1) (ablation)PosMLP-Video-S · Something-Something V1 (no pretraining)Top-1 accuracy (%): 43.90 -> 46.31Improved
raise group number to (12,24,48,96) (ablation)PosMLP-Video-S · Something-Something V1 (no pretraining)Top-1 accuracy (%): 46.31 -> 45.96Hurt
use learnable relative position encoding (LRPE) instead of GQPE (ablation)PosMLP-Video-S · Something-Something V1 (no pretraining)Top-1 accuracy (%): 38.06 -> 46.31Improved

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