CORTEXA
← Browse
arxivcs.CVcs.AI2026-06-29

SUMO: Segment and Track Any Motion with Nonlinear State Space Models

Kexin Tian, Sixu Li, Keshu Wu, Yang Zhou, Zhengzhong Tu

Visual Object Tracking (VOT) and Moving Object Segmentation (MOS) are two fundamental tasks in computer vision that involve both spatial and temporal object dynamics. Existing methods rely predominantly on visual cues and thus often falter in real-world scenarios where object motions are inherently complex and nonlinear. To address this limitation, we propose SUMO, a zero-shot, training-free, unified framework integrating nonlinear dynamics with vision-based segmentation for accurate and consistent VOT and MOS. Specifically, we develop a nonlinear State Space Model (SSM) inspired by robotics principles to capture the complex object dynamics. Building on this model, we propose a Selective Unscented Filter (SUF) for accurate state estimation, which features a joint scoring mechanism and dynamically fuses multi-source predictions to identify the most plausible object state over time. Furthermore, we apply a memory selection mechanism to evaluate the reliability of memory frames. Our extensive experimental results show that SUMO achieves state-of-the-art performance on both VOT and MOS tasks.

View free PDFSource page

Related papers

arxivcs.CVcs.AI2026-07-03

MambaLIE: Scene Light Intensity-Boosted Low-Light Image Enhancement with State Space Model

Wanshu Fan, Xiangyu Li, Cong Wang, Kin-man Lam, Xin Yang, Haiyan Zhang, et al.

Images captured by consumer electronic devices, such as mobile phones and digital cameras, often suffer from low-light degradation due to sensor limitations and imaging pipelines, which degrades visual quality and affects downstream vision tasks. Existing methods based on Convolu…

View free PDFSource page
arxivcs.CVcs.AI2026-07-22

Physics-Aware Complex-Valued State Space Model with Scattering-Prior Feature Modulation for PolSAR Image Classification

Fangyan Zhang, Fan Zhang, Shiqi Zhou, Jun Ni, Carlos López-Martínez, Qiang Yin

Polarimetric synthetic aperture radar (PolSAR) image classification is a representative task for physics-aware GeoAI, where land-cover semantics are closely coupled with electromagnetic scattering mechanisms. Many existing complex-valued networks can preserve amplitude-phase info…

View free PDFSource page
arxiveess.IVcs.AIcs.CV2026-07-15

ViPSAM: Visual Prompting Medical Image Segmentation Using Segment Anything Model

San Lee, Nalee Kim, Jeong Il Yu, Hee Chul Park, Boah Kim

In proton therapy planning, respiratory-gated non-contrast CT (NCCT) is commonly used for lesion segmentation; however, accurate delineation remains challenging due to low lesion-to-background contrast. Although learning-based methods have shown strong performance, they often str…

View free PDFSource page
arxivcs.CVcs.AIcs.LG2026-07-15

Beyond scalar losses: calibrating segmentation models via gradient vector field surgery

Laurin Lux, Alexander H. Berger, Moritz Knolle, Daniel Rückert, Johannes C. Paetzold

Region-based loss functions, such as the Dice loss, have established themselves as the de facto standard for highly class- and region-imbalanced segmentation tasks. However, models trained using region-based loss functions are notoriously miscalibrated and typically yield over-co…

View free PDFSource page
arxivcs.CVcs.AI2026-06-27

Flow Matching in Feature Space for Stochastic World Modeling

Francois Porcher, Nicolas Carion, Karteek Alahari, Shizhe Chen

World modeling requires forecasting uncertain futures while preserving information useful for downstream perception. Existing visual world models often struggle to satisfy both goals: VAE-based stochastic models operate in low-dimensional reconstruction latents, which can limit p…

View free PDFSource page
arxivcs.CVcs.AI2026-07-16

FoMoVLA: Bridging Visual Foresight and Motion Guidance for Vision-Language-Action Models

Wei Li, Peijin Jia, Yuan Ma, Xuefeng Jiang, Titong Jiang, Sheng Sun, et al.

Vision-Language-Action (VLA) models have achieved impressive results in visuomotor policy learning, yet remain fundamentally reactive, mapping current observations and language to actions without explicit forward prediction of world dynamics. Existing visual foresight methods pre…

View free PDFSource page