AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

TranSG: Transformer-Based Skeleton Graph Prototype Contrastive Learning With Structure-Trajectory Prompted Reconstruction for Person Re-Identification

Haocong Rao, Chunyan Miao

CVPR 2023 · Graph learning › Graph self-supervised learning · approach: Augmentation-free graph learning · 54 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 graph-based full-relation learning with SGT to the raw-joint baseline (ablation)TranSG · BIWI-SmAP: 9.3 -> 19.0Improved
Add graph-based full-relation learning with SGT to the raw-joint baseline (ablation)TranSG · BIWI-SR1: 24.8 -> 42.4Improved
Replace direct supervised learning with graph prototype contrastive learning (ablation)SGT · BIWI-SmAP: 19.0 -> 26.7Improved
Replace direct supervised learning with graph prototype contrastive learning (ablation)SGT · BIWI-SR1: 42.4 -> 66.6Improved
Add structure-trajectory prompted reconstruction (ablation)SGT + GPC · BIWI-SmAP: 26.7 -> 30.1Improved
Add structure-trajectory prompted reconstruction (ablation)SGT + GPC · BIWI-SR1: 66.6 -> 68.7Improved
Use naive prototype contrastive learning on original sequences instead of the raw-joint baseline (ablation)TranSG ablation · BIWI-SmAP: 9.3 -> 11.3Improved
Use naive prototype contrastive learning on original sequences instead of the raw-joint baseline (ablation)TranSG ablation · BIWI-SR1: 24.8 -> 38.1Improved
Use TranSG on unlabeled skeletons rather than SPC-MGRUnsupervised person re-identification · BIWI-SmAP: 16.0 -> 14.2Hurt
Use TranSG on unlabeled skeletons rather than SPC-MGRUnsupervised person re-identification · BIWI-SR1: 34.1 -> 42.2Improved

Later papers that compared with this method

1 later accepted paper reports TranSG as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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