AI Paper Atlas

Research map / Video / Action recognition

SkeleTR: Towards Skeleton-based Action Recognition in the Wild

Haodong Duan, Mingze Xu, Bing Shuai, Davide Modolo, Zhuowen Tu, Joseph Tighe, Alessandro Bergamo

ICCV 2023 · Video › Action recognition · approach: Skeleton-based action recognition · 48 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 transformer inter-sequence modeling (ablation)SkeleTR-S · PoseticsTop-1 accuracy (%): 48.21 -> 52.81Improved
use transformer encoders instead of non-local block (ablation)inter-sequence modeling · PoseticsTop-1 accuracy (%): 48.43 -> 52.81Improved
use Mix Pooling instead of single 1x1 pooling (ablation)SkeleTR-S · PoseticsTop-1 accuracy (%): 52.81 -> 53.90Improved
use full T x P feature aggregation instead of Mix Pooling (ablation)SkeleTR-S · PoseticsTop-1 accuracy (%): 52.78 vs 53.90; 5.211 vs 0.594 GFLOPsNo clear effect
adaptive sequence number M instead of fixed (ablation)SkeleTR-L · PoseticsTop-1 and GFLOPs: 54.95 -> 55.06; 6.653 -> 4.934 GFLOPsNo clear effect
use many short sequences (40x15) instead of few long sequences (2x300) (ablation)SkeleTR · PoseticsTop-1 accuracy (%): +2.1% (SkeleTR-S), +3% (SkeleTR-L)Improved
joint training on Posetics and AVA instead of AVA from scratch (ablation)SkeleTR-S · AVA v2.2 (10s window)overall mAP: 21.33 -> 25.69Improved
pretrain on Posetics then finetune on AVA (ablation)SkeleTR-S · AVA v2.2 (10s window)overall mAP: 21.33 -> 23.11Improved
late-fuse SkeleTR with RGB recognizerTimeSformer / ACAR-R101 · AVA v2.2overall mAP: 31.30 -> 34.34Improved
use SkeleTR short-sequence design with multi-person modeling instead of ST-GCN++Posetics classification · PoseticsTop-1 accuracy (%): 54.1 -> 57.9Improved
use short sequence format when ground-truth skeleton sequences are availableSkeleTR · tracked skeleton inputaccuracyNo clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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