Video Decoupling Networks for Accurate, Efficient, Generalizable, and Robust Video Object Segmentation

作者：Jisheng Dang, Huicheng Zheng, Yulan Guo, Jianhuang Lai, Bin Hu, Tat-Seng Chua · 发表于：IEEE Transactions on Image Processing · 年份：2026 · DOI：10.1109/tip.2025.3649360 · 被引用次数：3 · 研究领域：Visual Attention and Saliency Detection、Advanced Neural Network Applications、Human Pose and Action Recognition

Video object segmentation (VOS) is a fundamental task in video analysis, aiming to accurately recognize and segment objects of interest within video sequences. Conventional methods, relying on memory networks to store single-frame appearance features, face challenges in computational efficiency and capturing dynamic visual information effectively. To address these limitations, we present a Video Decoupling Network (VDN) with a per-clip memory updating mechanism. Our approach is inspired by the dual-stream hypothesis of the human visual cortex and decomposes multiple previous video frames into fundamental elements: scene, motion, and instance. We propose the Unified Prior-based Spatio-temporal Decoupler (UPSD) algorithm, which parses multiple frames into basic elements in a unified manner. UPSD continuously stores elements over time, enabling adaptive integration of different cues based on task requirements. This decomposition mechanism facilitates comprehensive spatial-temporal information capture and rapid updating, leading to notable enhancements in overall VOS performance. Extensive experiments conducted on multiple VOS benchmarks validate the state-of-the-art accuracy, efficiency, generalizability, and robustness of our approach. Remarkably, VDN demonstrates a significant performance improvement and a substantial speed-up compared to previous state-of-the-art methods on multiple VOS benchmarks. It also exhibits excellent generalizability under domain shift and robustness ...