AI Paper Atlas

Research map / Point clouds / Point cloud classification

GLT-T: Global-Local Transformer Voting for 3D Single Object Tracking in Point Clouds

Jiahao Nie, Zhiwei He, Yuxiang Yang, Mingyu Gao, Jing Zhang

AAAI 2023 · Point clouds › Point cloud classification · approach: Scene flow and dynamic point clouds · 50 citations (OpenAlex)

Read the paper

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
Replace VoteNet voting with the GLT module (ablation)GLT-T voting scheme on KITTI Car · KITTI CarSuccess: 61.7 -> 66.4Improved
Replace VoteNet voting with the GLT module (ablation)GLT-T voting scheme on KITTI Car · KITTI CarPrecision: 76.1 -> 80.7Improved
Add the importance-weighted training strategy to GLT (ablation)GLT-T on KITTI Car · KITTI CarSuccess: 66.4 -> 68.2Improved
Add the importance-weighted training strategy to GLT (ablation)GLT-T on KITTI Car · KITTI CarPrecision: 80.7 -> 82.1Improved
Add the global transformer block (ablation)GLT-T voting module on KITTI Car · KITTI CarSuccess: 61.7 -> 64.8Improved
Add the global transformer block (ablation)GLT-T voting module on KITTI Car · KITTI CarPrecision: 76.1 -> 79.0Improved
Add the local transformer block after the global transformer (ablation)GLT-T voting module on KITTI Car · KITTI CarSuccess: 64.8 -> 66.4Improved
Add the local transformer block after the global transformer (ablation)GLT-T voting module on KITTI Car · KITTI CarPrecision: 79.0 -> 80.7Improved
Use sparse sampling size m=16 instead of m=4 (ablation)GLT-T global transformer · KITTI CarSuccess: 61.3 -> 68.2Improved
Increase sparse sampling size from m=16 to m=32 (ablation)GLT-T global transformer · KITTI CarSuccess: 68.2 -> 67.6Hurt
Increase sparse sampling size from m=16 to m=32 (ablation)GLT-T global transformer · KITTI CarFLOPs / G: 3.56 -> 6.79Hurt
Set local KNN sampling size to n=8 rather than n=16 (ablation)GLT-T local transformer · KITTI CarSuccess: 68.2 -> 66.3Hurt

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