AI Paper Atlas

Research map / Detection and segmentation / 3D detection and driving

Spatial-Temporal Graph Enhanced DETR Towards Multi-Frame 3D Object Detection

Yifan Zhang, Zhiyu Zhu, Junhui Hou, Dapeng Oliver Wu

TPAMI 2024 · Detection and segmentation › 3D detection and driving · approach: Unified LiDAR 3D detection · 16 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
process multi-frame input as sequence with ConvGRU instead of concatenation (ablation)STEMD · Waymo val L2 (4 frames)mAPH: 69.62 -> 70.10Improved
add spatial-temporal graph attention network (ablation)STEMD · Waymo val L2 (4 frames)mAPH: 70.10 -> 72.15Improved
add temporal query recollection (ablation)STEMD · Waymo val L2 (4 frames)mAPH: 72.15 -> 72.87Improved
add IoU regularization term (ablation)STEMD · Waymo val L2 (4 frames)mAPH: 72.87 -> 73.75Improved
use STGA-Net instead of conventional multi-head self-attention (ablation)STEMD · Waymo val L2 (4 frames)mAPH: 71.85 -> 73.75Improved
use feature-based learned edge weights instead of distance-based (ablation)STGA-Net · Waymo val L2mAPH: 71.17 -> 73.75Improved
add both spatial self-attention and temporal cross-attention (ablation)STGA-Net · Waymo val L2mAPH: 71.56 -> 73.75Improved
add only temporal cross-attention (ablation)STGA-Net · Waymo val L2mAPH: 71.56 -> 71.69Improved
remove edge limit (no limit versus 5 edges per node) (ablation)STGA-Net · Waymo val L2mAPH: 71.74 -> 73.75Improved
use 16-frame STEMD versus concatenation baseline (ablation)STEMD · Waymo val L2 (16 frames)mAPH: 69.65 -> 74.56Improved
increase concatenated frames from 8 to 16 (ablation)Concat baseline · Waymo val L2mAPH: 69.68 -> 69.65No clear effect
recollect 300 queries from last frame (ablation)STEMD · Waymo val L2mAPH: 73.12 -> 73.75Improved

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