We present our solution for the MOSEv2 track of the 8th Large-scale Video Object Segmentation (LSVOS) Challenge at ECCV 2026. The challenge evaluates robust video object segmentation under complex temporal dynamics, including long-term occlusion, disappearance and reappearance, large appearance changes, and strong interference from visually similar objects. Our method builds on SAM3 and focuses on its memory readout. Standard target-only memory retrieval can confuse the annotated target with same-class non-target objects because such distractors are represented only implicitly as background. Our method introduces Competitive Memory Readout, which explicitly incorporates same-class competitor evidence when retrieving target information from memory. To prevent excessive suppression of weak or reappearing targets, we further apply a lightweight adaptive restoration rule after competition. The resulting system retains the original SAM3 tracking pipeline while improving target identity preservation in challenging videos. Our submission achieves 66.20 on the primary challenge score and ranks 2nd in the MOSEv2 track.
Figures & tables
Figure 1: Overview of the competitive memory readout. (a) Standard target-only memory readout retrieves target evidence without modelling visually similar non-target objects, which can lead to identity drift. (b) Our method additionally introduces same-class non-target objects as competitors during memory readout, suppressing distractor-supported target responses and improving target identity preservation.
Rank
Participant
J&F
J
F˙
J&Fd
J&Fr
F
J&F
1
HITsz-Dragon
69.82
68.21
71.43
79.12
34.87
73.76
70.99
2
mmm
66.20
64.79
67.60
81.57
26.88
69.74
67.26
3
kjeong
64.37
63.16
65.59
80.26
27.53
67.09
65.12
4
venuszhou
57.15
56.44
57.86
78.06
15.02
58.78
57.61
5
peterchao
55.03
54.21
55.84
76.25
14.83
57.09
55.65
6
ygz
54.87
54.18
55.57
72.15
14.50
56.76
55.47
Table 1: Official MOSEv2 track leaderboard of the 8th LSVOS Challenge. Date and submission ID are omitted. The mmm row corresponds to our submission.
Figure 2: Qualitative comparison over a challenging long video sequence. The rows show the ground truth, the SAM 3 baseline, and our method, respectively, with frames sampled from the beginning to the end of the sequence. Compared with the baseline, our method maintains more stable target segmentation under long-term appearance variation and distractor interference.
We present SAM3Dual, our third-place solution to the MOSEv2 track of the 8th Large-scale Video Object Segmentation (LSVOS) Challenge at ECCV 2026. SAM3Dual is a training-free inference extension of pretrained SAM 3 that explicitly separates temporal memory into a short-term branch for recent observations and a long-term branch for interval-sampled historical representations. The two memory responses are combined using a deterministic sequence-relative fusion schedule and conservatively modulated by the previous-frame object confidence. All pretrained SAM 3 parameters remain frozen, requiring no task-specific training, fine-tuning, test-time training, or online parameter optimization. The complete system achieved an official J&F score of 64.37 and ranked third in the MOSEv2 track. This result highlights the potential of reorganizing temporal memory entirely at inference time to obtain competitive long-term VOS performance while preserving the pretrained model.
This technical report explores the MOSEv2 track of the PVUW 2026 Challenge, which targets complex semi-supervised video object segmentation. Built on SAM3, we develop an automatic re-prompting framework to improve robustness under target disappearance and reappearance, severe transformation, and strong same-category distractors. Our method first applies the SAM3 detector to later frames to identify same-category object candidates, and then performs DINOv3-based object-level matching with a transformation-aware target feature pool to retrieve reliable target anchors. These anchors are injected back into the SAM~3 tracker together with the first-frame mask, enabling multi-anchor propagation rather than relying solely on the initial prompt. This simple directly benefits several core challenges of MOSEv2. Our solution achieves a J&F of 51.17% on the test set, ranking 3rd in the MOSEv2 track.
Mingqi Gao, Sijie Li, Jungong Han
School of Computer Science, University of Sheffield · Department of Automation, Tsinghua University
Complex video object segmentation requires robust target propagation under severe occlusion, disappearance and reappearance. Although SAM3 provides strong promptable mask propagation, a uniform inference path remains unreliable for tiny targets with insufficient visual evidence and semantic-dominated targets whose identities depend on explicit attributes. To this end, we present VOS-Agent, a collaborative framework that retains SAM3 as the shared dense segmentation module and conditionally activates specialized agents according to target characteristics. A Target Perception and Routing Agent assigns each sequence to a regular, tiny, or semantic-dominated route. Tiny targets are supported by a Visual Tracking Agent through confidence-aware box prompts, while semantic-dominated targets are handled by an MLLM-based Semantic Agent through description-guided localization and candidate verification. On the MOSEv2 test set, VOS-Agent achieves 69.82% on the official J&F˙ metric and ranks first in the MOSEv2 Track of the 8th LSVOS Challenge at ECCV 2026.
Canyang Wu, Jinrong Zhang, Xusheng He +3
Harbin Institute of Technology, Shenzhen · Nanyang Technological University · Shenzhen Loop Area Institute