AI Paper Atlas

Research map / Learning theory and algorithms / Clustering

SynMVCrowd: A Large Synthetic Benchmark for Multi-view Crowd Counting and Localization

Qi Zhang, Daijie Chen, Yunfei Gong, Hui Huang

IJCV 2026 · Learning theory and algorithms › Clustering · approach: Incomplete multi-view clustering · 1 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
use ResNet18 backbone instead of VGG19 (ablation)Baseline (OT) · SynMVCrowd countingMAE: 59.04 -> 50.20Improved
use ResNet18 backbone instead of Transformer (ablation)Baseline (OT) · SynMVCrowd countingMAE: 66.23 -> 50.20Improved
use optimal transport loss instead of MSE lossBaseline · SynMVCrowd multi-view countingMAE: 68.79 -> 50.20Improved
use optimal transport loss instead of MSE lossBaseline · SynMVCrowd multi-view localizationMODA: 34.6 -> 49.6Improved
add spatial feature selection module (ablation)Baseline (MSE) · SynMVCrowd multi-view countingMAE: 74.33 -> 68.79Improved
add spatial feature selection module (ablation)Baseline (OT) · SynMVCrowd multi-view countingMAE: 52.94 -> 50.20Improved
add spatial feature selection module (ablation)Baseline (OT) · SynMVCrowd multi-view localizationMODA: 46.7 -> 49.6Improved
test with 9 camera views instead of 3 views (ablation)Baseline (OT) · SynMVCrowd multi-view countingMAE: 57.97 -> 42.46Improved
test with 9 camera views instead of 3 views (ablation)CountFormer · SynMVCrowd multi-view countingMAE: 47.71 -> 77.82Hurt
use more frontal camera pitch ([-30, 0] instead of [-90,-60)) (ablation)Baseline (OT) · SynMVCrowd multi-view countingMAE: 48.19 -> 55.97Hurt
add domain adaptation to fine-tuning on 100% Wildtrack labels (ablation)Baseline · WildtrackMODA: 85.9 -> 88.7Improved
add unsupervised domain adaptation to SynMVCrowd-trained counter (ablation)Baseline counting model · ShanghaiTech AMAE: 187.70 -> 118.70Improved

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