CAMotion | Dataset & Benchmark

Introduction

Camouflaged motion object detection and segmentation aim to find targets that blend with the background while moving in video. Many existing benchmarks emphasize salient or clearly visible objects; subtle camouflage combined with motion ambiguity remains under-explored. CAMotion is a large-scale benchmark for studying camouflaged moving objects in realistic in-the-wild videos, with dense annotations and standardized splits for reproducible comparison.

The dataset focuses on challenging factors including low contrast, background blending, clutter, occlusion, motion ambiguity, and changing illumination—supporting both segmentation-oriented pipelines and motion-guided video understanding methods.

[TBD：在此补充与论文 Introduction 一致的贡献点 1–3 句；可加入与 COD10K / MoCA 等工作的对比定位]

Statistics

Camouflaged motion in unconstrained real-world video

Dense scenarios with clutter, occlusion, and camera motion

High-quality mask annotations for fair training and evaluation

Standard splits and benchmark protocol

[TBD：四格短句可对齐论文 Statistics 小节卖点，或改成与 MOSE 相同的统计维度描述]

REPLACEVideos

REPLACEFrames

REPLACECategories

REPLACEAnnotations

Table 1. Statistical comparison between CAMotion and related camouflage / video segmentation datasets. [TBD：列名、行（数据集名）与数字从论文 Table 1 粘贴；若暂无表图可保留占位或换为一张静态图 assets/table1.png]

Dataset	Videos	Frames	Annotations	Notes
COD10K (example)	—	—	—	[TBD]
MoCA (example)	—	—	—	[TBD]
CAMotion	REPLACE	REPLACE	REPLACE	Ours

Official splits

Split	Videos	Frames	Notes
Train	REPLACE	REPLACE	Standard training split
Val	REPLACE	REPLACE	Validation / ablation
Test	REPLACE	REPLACE	Held-out evaluation

[TBD：若论文中有 Challenge 分布图，在下方插入 <img src="assets/challenge_dist.png" alt="" />]

Demo

Representative challenge categories in CAMotion. [TBD：与论文 Fig. 中类别命名对齐]

[TBD：按论文增加更多子类图块；Tab 的 data-filter 需与每个 figure 的 data-cat 一致]

Video teaser

[TBD：嵌入 MP4 / YouTube / Bilibili iframe]

Tasks & Evaluation

We report results under a unified protocol: define input (e.g., first-frame mask or box), allowed pretraining, and evaluation metrics. [TBD：1–2 句概括主实验设定，可引用论文 Sec.]

Metrics: mIoU, F-measure / S-measure, MAE [TBD：与终稿一致]
Protocol: [TBD：是否允许光流/外训数据等]
Test submission: [TBD：评测服务器提交流程一句话]

Table 2. Main benchmark results on CAMotion (placeholder). [TBD：从论文主表复制；可加「相对基线降幅」等一句 MOSE 式总结]

Method	Backbone	Setting	mIoU	MAE
Baseline-A	REPLACE	Sup.	REPLACE	REPLACE
Baseline-B	REPLACE	Sup.	REPLACE	REPLACE
Ours	REPLACE	Sup.	REPLACE	REPLACE

Full leaderboard on Evaluation Server

Dataset

Dataset Download

The dataset is available for non-commercial research purposes only. Please use the following links.

[TBD：若与机构协议有关，粘贴许可声明原文或链接]

Hugging Face [TBD：填写实际 HF 数据集名] Google Drive [TBD：或改为百度网盘等]

[TBD：若仅一个源，删除多余卡片并把 href 改为 REPLACE_WITH_*]

Evaluation

Please submit results on the validation / test protocol as specified in the paper.

Codabench / Evaluation Server [TBD：平台名称与链接]

Data

CAMotion contains REPLACE videos and REPLACE high-quality masks for REPLACE objects across REPLACE categories. [TBD：与论文 Dataset 段数字一致]

Evaluation metrics follow standard segmentation practice (e.g., mIoU, boundary scores). [TBD]
For validation, first-frame annotations are released for the evaluated targets. [TBD：若与 MOSE 不同请改写]
Test-set policy: [TBD：公开/仅服务器/竞赛期开放等]

Data structure

train_valid.tar.gz
│
├── Annotations
│   ├── video_name_1
│   │   ├── 00000.png
│   │   └── ...
│   └── ...
│
└── JPEGImages
    ├── video_name_1
    │   ├── 00000.jpg
    │   └── ...
    └── ...

[TBD：按实际压缩包目录修改；与官方 README 完全一致]

Annotations only REPLACE size Splits & metadata REPLACE size Codebase GitHub

Usage notice. CAMotion is released for non-commercial research use. Please cite the paper and follow the license terms. [TBD：若采用 CC-BY-NC-SA 等，写明与 MOSE 相同或附许可证链接]

People

Siyuan Yao

[TBD：单位]

Hao Sun

[TBD：单位]

Hai Long

[TBD：单位]

Ruiqi Yu

[TBD：单位]

Jiehong Li

[TBD：单位]

Xiwei Jiang

[TBD：单位]

Yanzhao Su

[TBD：单位]

Wenqi Ren

[TBD：单位]

Xiaochun Cao

[TBD：单位 · 通讯作者可在此标注]

Citation

Please cite CAMotion if it helps your research.

@article{camotion,
  title   = {CAMotion: A High-Quality Dataset for Camouflaged Motion Object Detection in the Wild},
  author  = {Siyuan Yao and Hao Sun and Hai Long and Ruiqi Yu and Jiehong Li and Xiwei Jiang and Yanzhao Su and Wenqi Ren and Xiaochun Cao},
  journal = {Under review},
  year    = {2026}
}

[TBD：录用后替换 journal / 会议名、卷期、页码、DOI]

Related work

[TBD：可选：粘贴相关数据集或方法的 BibTeX，与 MOSE 页「Our related works」类似]

FAQ

How do I evaluate on the test split?

[TBD：作答]

Can I use external training data?

[TBD：作答]

Where to report issues?

[TBD：GitHub Issues / 邮箱]