AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

MessyTable: Instance Association in Multiple Camera Views

Zhongang Cai, Junzhe Zhang, Daxuan Ren, Cunjun Yu, Haiyu Zhao, Shuai Yi, Chai Kiat Yeo, Chen Change Loy

ECCV 2020 · Detection and segmentation › Open-set and few-shot detection · approach: Object-level representation learning · 14 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 a separate surrounding branch (ASNet) instead of an appearance-only triplet network (ablation)TripletNet · MessyTable (all scenes)AP: 0.467 -> 0.524Improved
naively zoom out the input crop to include surroundings (ablation)TripletNet · MessyTable (all scenes)AP: 0.467 -> 0.430Hurt
add the epipolar soft constraint (ablation)ASNet · MessyTable (all scenes)AP: 0.524 -> 0.577Improved
add the epipolar soft constraint (ablation)ASNet · MessyTable (all scenes)IPAA-100: 0.170 -> 0.219Improved
use a deeper backbone (ablation)MatchNet · MessyTable (all scenes)AP: 0.193 -> 0.138Hurt
use a deeper backbone (ablation)DeepCompare · MessyTable (all scenes)AP: 0.202 -> 0.129Hurt
use a deeper backbone (ablation)DeepDesc · MessyTable (all scenes)AP: 0.090 -> 0.171Improved
use triplet architecture instead of Siamese patch-matching modelsMatchNet / DeepCompare / DeepDesc · MessyTable (all scenes)AP: 0.467 vs 0.193, 0.202, 0.090Improved
test on harder scenes (Medium and Hard vs Easy)ASNet+ESC · MessyTable (Easy/Medium/Hard)AP: 0.709 -> 0.594 -> 0.457Hurt
pretrain on MessyTable instead of ImageNetASNet · MPII MKAP: 0.881 -> 0.905Improved
pretrain on MessyTable instead of ImageNetASNet · EPFL MVMCAP: 0.950 -> 0.969Improved
pretrain on MessyTable instead of ImageNetASNet · WILDTRACKAP: 0.718 -> 0.734Improved

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