SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2507.00648 · ICCV · 2025

UMDATrack: Unified Multi-Domain Adaptive Tracking Under Adverse Weather Conditions

Rui Zhu, Ziqi Wang, Xiaochun Cao, Wenqi Ren, Siyuan Yao, Yanyang Yan

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 2 functions out of this paper's own repositories and ran 2 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
Z-Z188/UMDATrack — 1 of 1
copy not recorded — 1 of 1
FunctionStatusWhere it lives
UMDATrack Ran Z-Z188/UMDATrack/lib/models/UMDATrack/UMDATrack.py
code served (permissive licence) · get_code("26e86bead3098467")
box_xyxy_to_cxcywh Ran this paper's copy was not recorded; identical code first harvested from edward-sun/tsp-detection
pointer only · get_code("031b02fb990284ba")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Visual object tracking has gained promising progress in past decades. Most of the existing approaches focus on learning target representation in well-conditioned daytime data, while for the unconstrained real-world scenarios with adverse weather conditions, e.g. nighttime or foggy environment, the tremendous domain shift leads to significant performance degradation. In this paper, we propose UMDATrack, which is capable of maintaining high-quality target state prediction under various adverse weather conditions within a unified domain adaptation framework. Specifically, we first use a controllable scenario generator to synthesize a small amount of unlabeled videos (less than 2% frames in source daytime datasets) in multiple weather conditions under the guidance of different text prompts. Afterwards, we design a simple yet effective domain-customized adapter (DCA), allowing the target objects' representation to rapidly adapt to various weather conditions without redundant model updating. Furthermore, to enhance the localization consistency between source and target domains, we propose a target-aware confidence alignment module (TCA) following optimal transport theorem. Extensive experiments demonstrate that UMDATrack can surpass existing advanced visual trackers and lead new stateof-the-art performance by a significant margin. Our code is available at https://github.com/Z-Z188/UMDATrack.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2507.00648")
get_code_for_paper("2507.00648")
have("2507.00648")

Connect an agent — have() is free.