SAM3Dual is a training‑free inference extension of pretrained SAM 3 that won third place in the MOSEv2 track of the 8th Large‑scale Video Object Segmentation Challenge. It separates temporal memory into short‑term and long‑term branches, fuses their responses deterministically, and modulates them with previous‑frame confidence, all while keeping SAM 3 parameters frozen. The approach achieved an official J&F score of 64.37, demonstrating competitive long‑term VOS performance without task‑specific training.
By JeongRae Kim, Chaehyun Kim, Changwon Lim
Segmentation-based multi-object tracking (MOT) with foundation video models such as SAM2 offers strong localization quality, yet remains fragile in crowded, real-world scenes. In detector-prompted SAM...
arXiv:2605.12006v2 Announce Type: replace
Abstract: The performance of promptable video object segmentation (PVOS) models substantially degrades under input corruptions, which prevents PVOS deploymen...
By Sohyun Lee, Yeho Gwon, Lukas Hoyer, Konrad Schindler, Christos Sakaridis, Suha Kwak
LiAM‑SAM is a lifecycle‑aware memory framework designed to improve segmentation‑based multi‑object tracking (MOT) with the SAM2 foundation video model. It addresses three common failure modes—faulty track initiation, memory drift during close interactions, and unreliable re‑identification after occlusion—by introducing contrastive track initiation, motion‑ and geometry‑grounded memory correction, and adaptive context memory. The system achieves state‑of‑the‑art HOTA and IDF1 scores, with ablations showing significant gains in association metrics and a 96% reduction in identity switches.
By Gr\'egoire Francisco, Alessandro D'Amico, Samuele Costantini, Gianpiero Francesca, Lorenzo Garattoni
arXiv:2610.01022v1 Announce Type: new
Abstract: Memory-attention-based Video Instance Segmentation (VIS) methods have demonstrated strong zero-shot tracking capability, yet their substantial memory r...
By Arash Rocky, Q. M. Jonathan Wu
The paper introduces Event-Driven Refresh + Recurrence Memory (EDRRM) to improve Referring Video Object Segmentation (RVOS). EDRRM selectively re-invokes the Sa2VA model at stable change points, using an EMA‑smoothed event score from tracking cues and a recurrence memory that retrieves anchor frames via CLIP similarity. Experiments on Ref‑DAVIS17, MeViS, and ReVOS show that EDRRM maintains or surpasses J&F scores while reducing refresh calls and false‑positive failures, with modest overhead compared to Sa2VA inference.
By Abu Hanif Muhammad Syarubany, Jaehyun Jang, Siwoo Lim, Seungyeon Ryu, Chang D. Yoo
The paper introduces Savvy, a zero‑shot, semi‑online, class‑agnostic system that persistently discovers objects and maintains their identities in long videos, and OGA, an evaluation suite that rewards coherent part‑level predictions even when their granularity differs from reference annotations. Savvy combines modular mask discovery, deferred admission based on accumulated evidence, and track consolidation to keep an evolving object set, outperforming DEVA+SAM and EntitySAM on ScanNet and HM3D datasets in metrics such as VPQ_inf, STQ, and AQ. OGA further distinguishes coherent part‑level support from temporal identity failures, revealing that conventional one‑to‑one VPQ metrics are sensitive to annotation granularity and that temporal failures can be detected even when frame‑level masks remain unchanged.
By Qing Su, Kaiyang Li, Yuan Zhuang, Fei Miao, Shihao Ji
arXiv:2609.37339v1 Announce Type: new
Abstract: General multi-object tracking (GMOT) tracks all instances of a user-specified category from a single first-frame exemplar. Prior work relies on boundin...
By Jer Pelhan, Alan Lukezic, Matej Kristan
arXiv:2607. 17157v1 Announce Type: cross Abstract: Multi-object tracking (MOT) aims to localize multiple objects in videos while preserving their identities over time.
By Yanrong Qin, Xiaoyan Cao, Yao Yao
The paper presents CapMap-MS-TTA, a unified multimodal model that achieved third place in the MUMU track of the 8th Large-scale Video Object Segmentation Challenge. The solution tackles image tagging, open‑vocabulary object detection, and English captioning under strict resource limits, using an expanded keyword lexicon and lightweight expand‑hints for tagging, and Florence‑2 with multi‑scale and horizontal‑flip TTA plus label‑aware NMS for detection. The approach improves the reproduced Florence‑2 baseline from 15.16 to a best public score of 16.4815 without fine‑tuning.
By Chengfeng Qiu, Kaifeng Wei
LayerRecall is a memory router for autoregressive video diffusion that selectively retrieves and injects historical key/value states into specific layers of the model, based on the current context. It addresses the problem that existing memory mechanisms expose nonlocal history but do not guarantee effective use, by recognizing that different layers prefer current, recent, or distant context. The method, combined with Cross‑Horizon Prediction Matching, achieves state‑of‑the‑art long‑range consistency on MemoBench and MovieBench while maintaining local continuity and incurring negligible inference overhead.
By Yixuan Ding, Jiahao Kong, Wei Huang, Ruijie Quan, Yi Yang
arXiv:2607. 28627v1 Announce Type: cross Abstract: Long visual context poses a challenge for vision-language models: performance degrades as the number of distractors grows, and processing all tokens at once is computationally infeasible under GPU memory constraints.
By Yao Xiao, Reuben Tan, Zhen Zhu, Yuqun Wu, Jianfeng Gao, Derek Hoiem