AI Paper Atlas

Research map / Multi-agent systems and games / Human-AI and goal-conditioned

CATNet: Collaborative Alignment and Transformation Network for Cooperative Perception

Gong Chen, Chaokun Zhang, Tao Tang, Pengcheng Lv, Feng Li, Xin Xie

CVPR 2026 · Multi-agent systems and games › Human-AI and goal-conditioned · approach: Collaborative multi-agent perception · 0 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 STSync to baseline (ablation)intermediate-fusion baseline · OPV2VAP@0.5 / AP@0.7: 0.595/0.384 -> 0.818/0.678Improved
add STSync to baseline (ablation)intermediate-fusion baseline · DAIR-V2XAP@0.5 / AP@0.7: 0.659/0.461 -> 0.683/0.496Improved
add WTDen to baseline (ablation)intermediate-fusion baseline · OPV2VAP@0.5 / AP@0.7: 0.595/0.384 -> 0.645/0.461Improved
add AdpSel to baseline (ablation)intermediate-fusion baseline · OPV2VAP@0.5 / AP@0.7: 0.595/0.384 -> 0.624/0.425Improved
add WTDen on top of STSync (ablation)STSync · OPV2VAP@0.5: 0.818 -> 0.834Improved
add AdpSel on top of STSync+WTDen (full CATNet) (ablation)STSync + WTDen · DAIR-V2XAP@0.7: 0.549 -> 0.565Improved
add WTDen on top of STSync+AdpSel (full CATNet) (ablation)STSync + AdpSel · DAIR-V2XAP@0.7: 0.553 -> 0.565Improved
vary AdpSel retention ratio from 0.1 to 0.6 (ablation)standalone AdpSel · OPV2VAP@0.7: 0.674 (0.1) / 0.691 (0.3) / 0.663 (0.6)Mixed
mask high-attention regions selected by AdpSel (ablation)AdpSel · OPV2VAP@0.5: 0.897 -> 0.364Hurt
mask low-attention regions (ablation)AdpSel · OPV2VAP@0.5: 0.897 -> 0.784Hurt
CATNet vs second-best method under latency and noiseCATNet · V2XSetAP@0.5 / AP@0.7: 0.817 -> 0.858 / 0.624 -> 0.643Improved
increase max delay from 0ms to 500msCATNet · OPV2VAP@0.7: 0.763 -> 0.624Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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