AI Paper Atlas

Research map / Video / Action recognition

STM: SpatioTemporal and Motion Encoding for Action Recognition

Boyuan Jiang, MengMeng Wang, Weihao Gan, Wei Wu, Junjie Yan

ICCV 2019 · Video › Action recognition · approach: Spatiotemporal CNNs for action recognition · 503 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 CSTM and CMM (STM) to TSNTSN ResNet-50 · Something-Something v1 val (8 frames)top-1 accuracy: 19.7 -> 49.2Improved
add CMM to CSTM (ablation)STM · Something-Something v1 val (8 frames)top-1 accuracy: 47.7 -> 49.2Improved
add CSTM to CMM (ablation)STM · Something-Something v1 val (8 frames)top-1 accuracy: 44.1 -> 49.2Improved
add CSTM alone to TSN (ablation)TSN · Something-Something v1 val (8 frames)top-1 accuracy: 19.7 -> 47.7Improved
add CMM alone to TSN (ablation)TSN · Something-Something v1 val (8 frames)top-1 accuracy: 19.7 -> 44.1Improved
fuse CSTM and CMM by summation instead of concatenation (ablation)STM · Something-Something v1 val (8 frames)top-1 accuracy: 41.8 -> 49.2Improved
replace only one block with STM at stage 5 instead of stage 2 (ablation)STM · Something-Something v1 val (8 frames)top-1 accuracy: 38.7 -> 41.5Improved
replace one block per stage (4 blocks) instead of one block (ablation)STM · Something-Something v1 val (8 frames)top-1 accuracy: 41.5 -> 47.9Improved
replace all 16 blocks instead of 4 (ablation)STM · Something-Something v1 val (8 frames)top-1 accuracy: 47.9 -> 49.2Improved
use channel-wise instead of ordinary temporal convolution in CSTM (ablation)CSTM · Something-Something v1 val (8 frames)top-1 accuracy: 46.9 -> 47.7Improved
increase input from 8 to 16 framesSTM · Something-Something v1 valtop-1 accuracy: 49.2 -> 50.7Improved
use STM instead of TSM at 8 frames vs 16 framesSTM 8F vs TSM 16F · Something-Something v1 val (8 frames)top-1 accuracy: +2.7% accuracyImproved

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