AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

AlignTrack: Top-Down Spatiotemporal Resolution Alignment for RGB-Event Visual Tracking

Chuanyu Sun, Jiqing Zhang, Yang Wang, Yuanchen Wang, Yutong Jiang, Baocai Yin, Xin Yang

AAAI 2026 · Vision-language and multimodal › Cross-modal learning · approach: Multi-modality image fusion · 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
add TDA module (ablation)AlignTrack · FE240/CRSOT/VisEventSR: -2.7 average SR drop without itImproved
add CPA module instead of learnable tokens (ablation)AlignTrack · FE240/CRSOT/VisEventSR: 0.9% SR decrease without itImproved
add cross-fusion in CPA (ablation)AlignTrack · FE240SR: 67.3 -> 68.1Improved
add reconstruction loss (ablation)AlignTrack · FE240SR: 66.2 -> 68.1Improved
add CSA loss (ablation)AlignTrack · FE240/CRSOT/VisEventSR: 1.3% average SR drop without itImproved
add target cropping to CSA loss (ablation)AlignTrack · FE240SR: 65.6 -> 68.1Improved
use both RGB and Event inputs rather than RGB only (ablation)AlignTrack · FE240SR: 44.2 -> 68.1Improved
use both modalities rather than Event only (ablation)AlignTrack · CRSOTSR: 11.2 -> 63.0Improved
increase decoder layers from 3 to 12 (ablation)AlignTrack · FE240SR: 63.0 -> 68.1Improved
inject top-down signal into Value rather than Query (ablation)AlignTrack · FE240SR: 65.7 -> 68.1Improved
inject top-down signal into Value rather than Key (ablation)AlignTrack · FE240SR: 66.3 -> 68.1Improved
set lambda_rec to 0.1 instead of 1 (ablation)AlignTrack · FE240SR: 67.9 -> 68.1Improved

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