Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

The Third Visual Object Tracking Segmentation VOTS2025 Challenge Results

Kristan, M. ; Vu, X.-S. LU and Zhu, X. (2025) International Conference on Computer Vision In International Conference on Computer Vision Workshops (ICCV Workshops) p.7472-7490
Abstract
The VOTS2025 is the third edition of the Visual Object Tracking Segmentation benchmark. Organised the VOT initiative, VOTS builds on 10 years of experience in organising VOT challenges. Building on the tracking setup introduced in VOTS2023, the challenge continues to integrate short-term and long-term tracking, as well as single-target and multi-target scenarios, using segmentation masks as the sole form of target annotation. This year's benchmark features three sub-challenges. VOTS2025 and VOTSt2025, evaluate tracking of conventional objects and objects undergoing topological changes, respectively. A new addition, VOTS-RT2025, aims to foster the development of efficient tracking models by introducing constraints that highlight realtime... (More)
The VOTS2025 is the third edition of the Visual Object Tracking Segmentation benchmark. Organised the VOT initiative, VOTS builds on 10 years of experience in organising VOT challenges. Building on the tracking setup introduced in VOTS2023, the challenge continues to integrate short-term and long-term tracking, as well as single-target and multi-target scenarios, using segmentation masks as the sole form of target annotation. This year's benchmark features three sub-challenges. VOTS2025 and VOTSt2025, evaluate tracking of conventional objects and objects undergoing topological changes, respectively. A new addition, VOTS-RT2025, aims to foster the development of efficient tracking models by introducing constraints that highlight realtime performance. All sub-challenges adopt a consistent evaluation protocol, with VOTS-RT2025 introducing specific modifications to reflect latency-aware performance. We report and analyze results from 32 submissions. Full tracker descriptions, source code, datasetsand the evaluation toolkit are available on the project website11https://www.votchallenge.net/vots2025/. © 2025 IEEE. (Less)
Please use this url to cite or link to this publication:
author
; and
author collaboration
organization
publishing date
type
Chapter in Book/Report/Conference proceeding
publication status
published
subject
keywords
general object tracking, video object segmentation, visual object tracking, VOTS, Object tracking, Particle tracking, Target tracking, General object tracking, Long-term tracking, Multi-targets, Object Tracking, Segmentation masks, Topological changes, Tracking models, Video objects segmentations, Visual object tracking, Image segmentation
host publication
2025 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)
series title
International Conference on Computer Vision Workshops (ICCV Workshops)
pages
19 pages
conference name
International Conference on Computer Vision
conference location
Honolulu, United States
conference dates
2025-10-19 - 2025-10-23
external identifiers
  • scopus:105035209983
ISSN
2473-9944
2473-9936
ISBN
979-8-3315-8989-9
979-8-3315-8988-2
DOI
10.1109/ICCVW69036.2025.00771
language
English
LU publication?
yes
id
edaf6dd3-aa28-44c3-9f32-a88d20c557d6
date added to LUP
2026-07-02 11:44:47
date last changed
2026-09-24 18:28:33
@inproceedings{edaf6dd3-aa28-44c3-9f32-a88d20c557d6,
  abstract     = {{The VOTS2025 is the third edition of the Visual Object Tracking Segmentation benchmark. Organised the VOT initiative, VOTS builds on 10 years of experience in organising VOT challenges. Building on the tracking setup introduced in VOTS2023, the challenge continues to integrate short-term and long-term tracking, as well as single-target and multi-target scenarios, using segmentation masks as the sole form of target annotation. This year's benchmark features three sub-challenges. VOTS2025 and VOTSt2025, evaluate tracking of conventional objects and objects undergoing topological changes, respectively. A new addition, VOTS-RT2025, aims to foster the development of efficient tracking models by introducing constraints that highlight realtime performance. All sub-challenges adopt a consistent evaluation protocol, with VOTS-RT2025 introducing specific modifications to reflect latency-aware performance. We report and analyze results from 32 submissions. Full tracker descriptions, source code, datasetsand the evaluation toolkit are available on the project website11https://www.votchallenge.net/vots2025/. © 2025 IEEE.}},
  author       = {{Kristan, M. and Vu, X.-S. and Zhu, X.}},
  booktitle    = {{2025 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)}},
  isbn         = {{979-8-3315-8989-9}},
  issn         = {{2473-9944}},
  keywords     = {{general object tracking; video object segmentation; visual object tracking; VOTS; Object tracking; Particle tracking; Target tracking; General object tracking; Long-term tracking; Multi-targets; Object Tracking; Segmentation masks; Topological changes; Tracking models; Video objects segmentations; Visual object tracking; Image segmentation}},
  language     = {{eng}},
  pages        = {{7472--7490}},
  series       = {{International Conference on Computer Vision Workshops (ICCV Workshops)}},
  title        = {{The Third Visual Object Tracking Segmentation VOTS2025 Challenge Results}},
  url          = {{http://dx.doi.org/10.1109/ICCVW69036.2025.00771}},
  doi          = {{10.1109/ICCVW69036.2025.00771}},
  year         = {{2025}},
}