AI Paper Atlas

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

Learning Pseudo 3D Representation for Ego-centric 2D Multiple Object Tracking

Jiawei He, Lue Fan, Zhaoxiang Zhang

IJCV 2026 · Detection and segmentation › 3D detection and driving · approach: Depth-based and label-free 3D detection · 2 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 low-quality detection matching (ablation)modified DeepSORT baseline · WOD val FRONT cameraMOTA: 51.0 -> 53.4Improved
add GNN association learning (ablation)DeepSORT + low-quality dets · WOD val FRONT cameraMOTA: 53.4 -> 56.5Improved
add jointly learned 3D representation (ablation)P3DTrack · WOD val FRONT cameraMOTA: 56.5 -> 57.6Improved
add jointly learned 3D representation (ablation)P3DTrack · WOD val FRONT cameraIDF1: 66.5 -> 68.1Improved
add 2D Kalman motion to 2D feature (ablation)P3DTrack · WOD val FRONT cameraIDF1: 66.5 -> 58.6Hurt
use 3D representation instead of 3D Kalman motion without learned representation (ablation)P3DTrack · WOD val FRONT cameraIDF1: 63.3 -> 68.1Improved
use learned 3D representation instead of SfM 3D positions (ablation)P3DTrack · WOD val FRONT cameraMOTA: 55.5 -> 57.6Improved
use learned 3D representation instead of MiDaS v3 depth (ablation)P3DTrack · WOD val FRONT cameraIDF1: 63.4 -> 68.1Improved
raise detection threshold from 0.5 to 0.6 (ablation)P3DTrack · WOD val FRONT cameraMOTA: 57.6 -> 50.1Hurt
lower detection threshold from 0.5 to 0.4 (ablation)P3DTrack · WOD val FRONT cameraMOTA: 57.6 -> 51.4Hurt
raise appearance threshold from 0.6 to 0.7 (ablation)P3DTrack · WOD val FRONT cameraMOTA: 57.6 -> 58.0Mixed
use 3D similarity only (alpha 1.0) instead of alpha 0.4 (ablation)P3DTrack · WOD val FRONT cameraIDF1: 68.1 -> 54.2Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 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