YUV20K: A Complexity-Driven Benchmark and Trajectory-Aware Alignment Model for Video Camouflaged Object Detection

2026-04-11

AI Summary

This work addresses the challenges of video camouflaged object detection in complex dynamic scenes, where appearance instability and temporal feature misalignment hinder performance, compounded by the lack of high-difficulty benchmark datasets. To this end, the authors introduce YUV20K, the first large-scale pixel-level annotated benchmark specifically designed for six challenging scenarios, including large-displacement motion and camera movement. They further propose a novel framework that achieves frame-independent feature stabilization through semantic primitives and enhances temporal consistency via a trajectory-aware deformable alignment strategy. The method substantially outperforms state-of-the-art models on existing datasets and establishes a new baseline on YUV20K, demonstrating superior robustness under complex spatiotemporal variations and strong cross-domain generalization capabilities.

Technology Category

• Computer Vision: Motion & Tracking
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Security and Privacy: Large-scale security measurements
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Video Camouflaged Object Detection (VCOD) is currently constrained by the scarcity of challenging benchmarks and the limited robustness of models against erratic motion dynamics. Existing methods often struggle with Motion-Induced Appearance Instability and Temporal Feature Misalignment caused by complex motion scenarios. To address the data bottleneck, we present YUV20K, a pixel-level annoated complexity-driven VCOD benchmark. Comprising 24,295 annotated frames across 91 scenes and 47 kinds of species, it specifically targets challenging scenarios like large-displacement motion, camera motion and other 4 types scenarios. On the methodological front, we propose a novel framework featuring two key modules: Motion Feature Stabilization (MFS) and Trajectory-Aware Alignment (TAA). The MFS module utilizes frame-agnostic Semantic Basis Primitives to stablize features, while the TAA module leverages trajectory-guided deformable sampling to ensure precise temporal alignment. Extensive experiments demonstrate that our method significantly outperforms state-of-the-art competitors on existing datasets and establishes a new baseline on the challenging YUV20K. Notably, our framework exhibits superior cross-domain generalization and robustness when confronting complex spatiotemporal scenarios. Our code and dataset will be available at https://github.com/K1NSA/YUV20K

Problem

• Video Camouflaged Object Detection
• Motion-Induced Appearance Instability
• Temporal Feature Misalignment
• Complex Motion Scenarios
• Benchmark Scarcity

Innovation

• Video Camouflaged Object Detection
• Complexity-Driven Benchmark
• Motion Feature Stabilization
• Trajectory-Aware Alignment
• Temporal Feature Alignment