# 2nd Place Report of MOSEv2 Challenge 2025: Concept Guided Video Object Segmentation via SeC

Source: [2nd Place Report of MOSEv2 Challenge 2025: Concept Guided Video Object Segmentation via SeC](<https://www.sota2.com/research/paper/68fa7bb41e209131cea8a089>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T05:46:25.721Z

Authors: Zhixiong Zhang, Shuangrui Ding, Xiaoyi Dong, Yuhang Zang, Yuhang Cao, Jiaqi Wang

Published: 2025-09-28T12:26:03.000Z

## Abstract

Semi-supervised Video Object Segmentation aims to segment a specified target throughout a video sequence, initialized by a first-frame mask. Previous methods rely heavily on appearance-based pattern matching and thus exhibit limited robustness against challenges such as drastic visual changes, occlusions, and scene shifts. This failure is often attributed to a lack of high-level conceptual understanding of the target. The recently proposed Segment Concept (SeC) framework mitigated this limitation by using a Large Vision-Language Model (LVLM) to establish a deep semantic understanding of the object for more persistent segmentation. In this work, we evaluate its zero-shot performance on the challenging coMplex video Object SEgmentation v2 (MOSEv2) dataset. Without any fine-tuning on the training set, SeC achieved 39.7 \\JFn on the test set and ranked 2nd place in the Complex VOS track of the 7th Large-scale Video Object Segmentation Challenge.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2509.23838>)

[PDF](<https://arxiv.org/pdf/2509.23838.pdf>)
