AI Paper Atlas

Research map / Point clouds / Segmentation and detection

Graph Neural Network and Spatiotemporal Transformer Attention for 3D Video Object Detection From Point Clouds

Junbo Yin, Jianbing Shen, Xin Gao, David Crandall, Ruigang Yang

TPAMI 2021 · Point clouds › Segmentation and detection · approach: Single-stage point-voxel detection · 96 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 concatenation with GMPNet for short-term encoding (ablation)CenterPoint-PointPillars · nuScenes val (CenterPoint-PointPillars)mAP: 48.25 -> 49.78Improved
replace ConvGRU with AST-GRU for long-term aggregation (ablation)ConvGRU · nuScenes val (CenterPoint-PointPillars)mAP: 56.54 -> 57.96Improved
add spatial transformer attention (STA) to ConvGRU (ablation)ConvGRU · nuScenes val (CenterPoint-PointPillars)mAP: 56.54 -> 57.54Improved
add temporal transformer attention (TTA) on top of STA (ablation)STA-GRU · nuScenes val (CenterPoint-PointPillars)mAP: 57.54 -> 57.96Improved
use tracklet fusion instead of concatenation (ablation)concatenation · nuScenes val (CenterPoint-PointPillars)mAP: 49.35 -> 50.09Improved
use 3D ConvNet instead of concatenation (ablation)concatenation · nuScenes val (CenterPoint-PointPillars)mAP: 49.35 -> 52.84Improved
add GMPNet to AST-GRU (full online model) (ablation)AST-GRU · nuScenes val (CenterPoint-PointPillars)mAP: 57.96 -> 58.78Improved
use offline mode with future keyframes (ablation)Full Model (online) · nuScenes val (CenterPoint-PointPillars)mAP: 58.78 -> 59.37Improved
add motion map input to TTA (ablation)TTA · nuScenes val (TTA analysis)mAP: 26.03 -> 27.28Improved
use two TTA layers rather than one (ablation)TTA · nuScenes val (TTA analysis)mAP: 26.55 -> 27.28Improved
use three TTA layers rather than two (ablation)TTA · nuScenes val (TTA analysis)mAP: 27.28 -> 26.42Hurt
use video (VID) model instead of single-frame PointPillarsPointPillars · nuScenes testNDS: 45.3 -> 53.1Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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