arXiv Computer Vision

LiAM-SAM: Lifecycle-Aware Memory for Robust SAM2-Based MOT

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.

arXiv Computer Vision
Oct 1

Event-Driven Refresh and Recurrence Memory to Reduce Stale Grounding in Referring Video Object Segmentation

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
arXiv Computer Vision
Aug 31

LayerRecall: A State-Conditioned Memory Router for Long-Horizon Consistency in Video Generation

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 Computer Vision
Oct 7

Toward Open-World Video Segmentation over Long Horizons

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