UniMergeTrack: Hierarchical Model Merging for General RGB-X Visual Object Tracking
In this work, we present UniMergeTrack, a new model merging paradigm that preserves task-specific optimization while enabling effective cross-task knowledge integration.
ProofPaper ↗
Key points
- RGB-X tracking leverages complementary modalities, such as thermal infrared, event, or depth, to improve robustness under challenging conditions.
- Existing general-purpose RGB-X trackers typically follow two paradigms: independent task-specific training and joint training across modality combinations.
- UniMergeTrack first trains modality-specific trackers independently and then performs hierarchical model merging.
- Extensive experiments on the LasHeR, RGBT234, VisEvent, VOT-RGBD22, COESOT, and CDTB benchmarks demonstrate that UniMergeTrack achieves state-of-the-art or competitive performance across RGB-Thermal, RGB-Event, and RGB-Depth tracking tasks, while exhibiting strong generalization to unseen datasets.
Sources (1)
- [1]UniMergeTrack: Hierarchical Model Merging for General RGB-X Visual Object TrackingarXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 9, 06:05 AM
In this work, we present UniMergeTrack, a new model merging paradigm that preserves task-specific optimization while enabling effective cross-task knowledge integration.
RGB-X tracking leverages complementary modalities, such as thermal infrared, event, or depth, to improve robustness under challenging conditions.
Extractive summary: sentences quoted from the sources.
Before this
- Oct 9, 2026BLEND: Balancing Personalization vs. Generalization in Federated Vision-Language Models
- Oct 8, 2026StereoEngine: Scaling Stereo Bimanual Robot Data without Stereo Cameras
- Oct 8, 2026Microsoft Joins the Local AI Push
- Oct 8, 2026Understanding Jev, the new model everyone is talking about
- Oct 8, 2026SuperNav: An Agentic Navigation System for Any Task in Any Scene
- Oct 7, 2026[AINews] Claude Haiku 5.5 — better than GPT-6 Luna at the same pricing