AI Paper Atlas

Research map / Point clouds / Segmentation and detection

MLVSNet: Multi-Level Voting Siamese Network for 3D Visual Tracking

Zhoutao Wang, Qian Xie, Yu-Kun Lai, Jing Wu, Kun Long, Jun Wang

ICCV 2021 · Point clouds › Segmentation and detection · approach: Single-stage point-voxel detection · 66 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
replace TSFA with Target-Guided Attention (ablation)P2B · KITTI 3D tracking (Mean)Precision: 60.0 -> 62.3Improved
replace TSFA with Target-Guided Attention (ablation)P2B · KITTI 3D tracking (Mean)Success: 42.4 -> 42.3No clear effect
replace TSFA with TGA for efficiency (ablation)P2B · KITTI Cartesting speed (fps): 84 -> 93Improved
replace TSFA with TGA for efficiency (ablation)P2B · KITTI Cartraining time per epoch (min): 21 min -> 16 minImproved
add multi-level voting from last two layers (ablation)TGA model · KITTI 3D tracking (Mean)Success: 42.3 -> 44.4Improved
add multi-level voting from last two layers (ablation)TGA model · KITTI 3D tracking (Mean)Precision: 62.3 -> 64.9Improved
also vote from the shallowest layer (3+2+1 vs 3+2) (ablation)MLV · KITTI 3D tracking (Mean)Success: 44.4 -> 37.2Hurt
also vote from the shallowest layer (3+2+1 vs 3+2) (ablation)MLV · KITTI 3D tracking (Mean)Precision: 64.9 -> 55.6Hurt
vote from layers 3+2 instead of layer 3 only (ablation)MLV · KITTI 3D tracking (Mean)Success: 42.3 -> 44.4Improved
add Vote-cluster Feature Enhancement (ablation)MLVSNet · KITTI 3D tracking (Mean)Success: 44.4 -> 45.7Improved
add Vote-cluster Feature Enhancement (ablation)MLVSNet · KITTI 3D tracking (Cyclist)Success: 29.6 -> 34.3Improved
add Vote-cluster Feature Enhancement (ablation)MLVSNet · KITTI 3D tracking (Mean)Precision: 64.9 -> 66.6Improved

Later papers that compared with this method

2 later accepted papers report MLVSNet as a baseline in their results tables; 2 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