AI Paper Atlas

Research map / Learning theory and algorithms / Clustering

Mahalanobis Distance-based Multi-view Optimal Transport for Multi-view Crowd Localization

Qi Zhang, Kaiyi Zhang, Antoni B. Chan, Hui Huang

ECCV 2024 · Learning theory and algorithms › Clustering · approach: Incomplete multi-view clustering · 8 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 Gaussian density MSE loss with Euclidean multi-view optimal transport loss (ablation)multi-view crowd localization on CVCS · CVCSMODA: 18.6 -> 42.8Improved
add view-ray direction and object-to-camera distance to the Mahalanobis cost (M-MVOT vs E-MVOT) (ablation)E-MVOT · CVCSMODA: 42.8 -> 45.8Improved
add object-to-camera distance only (ED-MVOT) to Euclidean OT (ablation)E-MVOT · CVCSMODA: 42.8 -> 43.8Improved
M-MVOT instead of E-MVOT on MultiviewX (ablation)MVDeTr backbone · MultiviewXMODA: 96.3 -> 96.7Improved
penalize deviations along view ray more (sigma1^2 < sigma2^2) versus the reverse (ablation)MV-MVOT · MultiviewXMODP: 84.6 (1.2:1) -> 85.6 (1:1.2)Improved
select closest camera for each point instead of averaging camera losses (ablation)M-MVOT · MultiviewXMODA: 96.5 -> 96.7Improved
replace geometric covariance with learnable covariance matrix (ablation)M-MVOT · MultiviewXMODA: 96.7 -> 95.1Hurt
use single-image UOT with simple multi-view sum fusionmulti-view localization · MultiviewXMODA: 96.7 -> 23.9Hurt
replace MSE or Focal loss with M-MVOT (ablation)MVDeTr backbone · MultiviewXMODA: 93.9 (MSE) / 94.5 (Focal) -> 96.7Improved
increase alpha from 0.05 to 0.6 (ablation)M-MVOT · MultiviewXMODA: 96.7 -> 96.3Hurt
raise tau from 20 to 30 (ablation)M-MVOT · MultiviewXMODA: 96.7 -> 95.2Hurt
use M-MVOT instead of 3DROM on Wildtrackmulti-view localization · WildtrackMODA: 93.5 (3DROM) vs 92.1Hurt

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