AI Paper Atlas

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

XTrack: Multimodal Training Boosts RGB-X Video Object Trackers

Yuedong Tan, Zongwei Wu, Yuqian Fu, Zhuyun Zhou, Guolei Sun, Eduard Zamfir, Chao Ma, Danda Paudel, Luc Van Gool, Radu Timofte

ICCV 2025 · Vision-language and multimodal › Cross-modal learning · approach: Multi-modality image fusion · 30 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 shared expert (ablation)XTrack-B MeME · DepthTrackF-score: 57.6 -> 61.5Improved
add modality-specific experts (ablation)XTrack-B MeME · DepthTrackF-score: 59.1 -> 61.5Improved
add shared expert (ablation)XTrack-B MeME · VisEventPrecision: 76.2 -> 77.5Improved
add modality-specific experts (ablation)XTrack-B MeME · LasHeRPrecision: 67.8 -> 69.1Mixed
use two experts per modality instead of one (ablation)XTrack-B · DepthTrackF-score: 60.0 -> 61.5Improved
use two experts instead of three (ablation)XTrack-B · DepthTrackF-score: 60.9 -> 61.5Improved
train on event, depth and thermal instead of event only (ablation)XTrack-B · DepthTrackF-score: 45.5 -> 61.5Improved
train on event, depth and thermal instead of event only (ablation)XTrack-B · LasHeRPrecision: 58.1 -> 69.1Improved
add depth data to event training (ablation)XTrack-B · DepthTrackF-score: 45.5 -> 60.8Improved
add depth data to event training (ablation)XTrack-B · LasHeRPrecision: 58.1 -> 58.1No clear effect
use soft router (80%) instead of rigid classification (100%) (ablation)XTrack-B · DepthTrackF-score: 58.8 -> 61.5Improved
use 80% soft router instead of 33% near random assignment (ablation)XTrack-B · VisEventPrecision: 77.0 -> 77.5Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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