AI Paper Atlas

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

Learning And-Or Model to Represent Context and Occlusion for Car Detection and Viewpoint Estimation

Tianfu Wu, Bo Hu Li, Song Chun Zhu

TPAMI 2016 · Detection and segmentation › 3D detection and driving · approach: 3D objectness and scene segmentation · 49 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 multi-car context and occlusion modeling over DPMHierarchical And-Or model · KITTI (split trainset)AP: outperforms DPM by 9.1%Improved
add multi-car context and occlusion modeling over DPMHierarchical And-Or model · Parking LotAP: 55.2% AP, outperforms DPM by 10.9%Improved
add context to occlusion-only And-Or Structure (ablation)Hierarchical And-Or model · Street ParkingAP: 57.8% -> 62.1%Improved
replace greedy part selection with CAD-simulated semantic parts (ablation)AOG hierarchical model · Street ParkingAP: 62.1% -> 65.3%Improved
train on full KITTI training set instead of halfAOG+Greedy · KITTI test benchmark (Moderate)AP: 71.88% -> 75.94%Improved
train on full KITTI training set instead of halfAOG+Greedy · KITTI test benchmark (Easy)AP: 84.36% -> 84.80%Improved
train on full KITTI training set instead of halfAOG+Greedy · KITTI test benchmark (Hard)AP: 59.27% -> 60.70%Improved
use And-Or Structure with CAD-learned occlusion over DPMAnd-Or Structure · synthetic occlusion datasetAP: outperforms DPM by 7.2% in APImproved
use And-Or Structure over DPMAnd-Or Structure · PASCAL VOC2007 carAP: 58.2% -> 58.7%No clear effect
use hierarchical And-Or model over DPMAOG+Greedy · PASCAL VOC2007 carAP: 58.2% -> 60.6%Improved
use AOG over DPM on KITTI moderate/hardHierarchical And-Or model · KITTI test (Moderate, Hard)AP: above 10% in APImproved
use And-Or Structure for viewpoint estimation instead of VDPMAnd-Or Structure · PASCAL3D+ car (4 views)AVP: 20.2% -> 34.3%Improved

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