pith. machine review for the scientific record. sign in

arxiv: 2604.08287 · v2 · submitted 2026-04-09 · 💻 cs.CV

Recognition: 2 theorem links

· Lean Theorem

CAMotion: A High-Quality Benchmark for Camouflaged Moving Object Detection in the Wild

Siyuan Yao , Hao Sun , Ruiqi Yu , Xiwei Jiang , Wenqi Ren , Xiaochun Cao
Authors on Pith no claims yet

Pith reviewed 2026-05-10 18:34 UTC · model grok-4.3

classification 💻 cs.CV
keywords camouflaged object detectionvideo benchmarkmoving object detectioncomputer vision datasetocclusionmotion blurspecies diversity
0
0 comments X

The pith

A new benchmark dataset for camouflaged moving object detection in video covers diverse species and challenging conditions.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper seeks to overcome the limited scale and diversity of existing video camouflaged object detection datasets, which restrict training and evaluation of deep learning models. To do this the authors build CAMotion, a collection of video sequences that include many different species and incorporate attributes such as uncertain edges, occlusion, motion blur and shape complexity. Detailed annotations and statistical breakdowns of the sequences are supplied so that motion patterns of camouflaged objects can be examined across scenarios. The work also includes an evaluation of current leading models on the new data and outlines key remaining difficulties in the task. A sympathetic reader would care because larger and more varied video data directly supports better algorithm development for applications where camouflage must be overcome in natural footage.

Core claim

We construct CAMotion, a high-quality benchmark that covers a wide range of species for camouflaged moving object detection in the wild. CAMotion comprises various sequences with multiple challenging attributes such as uncertain edge, occlusion, motion blur, and shape complexity. The sequence annotation details and statistical distribution are presented from various perspectives, allowing CAMotion to provide in-depth analyses on the camouflaged object's motion characteristics in different challenging scenarios. Additionally, we conduct a comprehensive evaluation of existing SOTA models on CAMotion, and discuss the major challenges in VCOD task.

What carries the argument

The CAMotion benchmark itself, a set of annotated video sequences designed to capture camouflaged moving objects under varied real-world conditions and to supply statistical views of their motion attributes.

If this is right

  • Algorithms can be trained and tested on a larger and more varied collection of camouflaged video sequences than was previously available.
  • Motion characteristics of camouflaged objects can be studied across multiple species and under specific challenges such as blur or occlusion.
  • Weaknesses in current models become easier to identify through standardized evaluation on the supplied sequences and statistics.
  • Further progress in video camouflaged object detection becomes possible once researchers have access to the released benchmark and its annotations.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The availability of species-level diversity may allow future work to examine whether detection difficulty varies systematically by animal type or habitat.
  • The provided attribute annotations could support the creation of targeted test splits that isolate individual challenges such as motion blur.
  • If the benchmark is widely adopted, it may reduce reliance on synthetic or narrowly scoped data in related video detection studies.

Load-bearing premise

The new video sequences and their annotations possess enough quality and variety to support deeper analyses and more informative algorithm tests than earlier datasets provide.

What would settle it

A direct comparison showing that state-of-the-art models produce essentially the same accuracy rankings and error patterns on CAMotion as they do on prior smaller datasets would indicate that the new benchmark does not add the intended analytical power.

Figures

Figures reproduced from arXiv: 2604.08287 by Hao Sun, Ruiqi Yu, Siyuan Yao, Wenqi Ren, Xiaochun Cao, Xiwei Jiang.

Figure 1
Figure 1. Figure 1: Examples of our CAMotion dataset with corresponding pixel-level annotations. The first and third rows contain [PITH_FULL_IMAGE:figures/full_fig_p002_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Dataset features and species examples from CAMotion dataset. (a) Taxonomic structure of CAMotion. (b) The scale [PITH_FULL_IMAGE:figures/full_fig_p004_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Visualization of the challenging attributes in CAMotion. Best viewed in color and zoomed in for details. [PITH_FULL_IMAGE:figures/full_fig_p005_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Examples of refined initial annotations. White denotes [PITH_FULL_IMAGE:figures/full_fig_p005_4.png] view at source ↗
Figure 6
Figure 6. Figure 6: Visual comparison with state-of-the-art methods in challenging scenarios, [PITH_FULL_IMAGE:figures/full_fig_p008_6.png] view at source ↗
Figure 7
Figure 7. Figure 7: Optical flow and depth properties visualization. Each group comprises the original image, pixel-level annotation, [PITH_FULL_IMAGE:figures/full_fig_p009_7.png] view at source ↗
Figure 10
Figure 10. Figure 10: As illustrated in Fig. 10 (b), the MoCA-Mask testing [PITH_FULL_IMAGE:figures/full_fig_p009_10.png] view at source ↗
Figure 8
Figure 8. Figure 8: Visualization of SOTA method performances on [PITH_FULL_IMAGE:figures/full_fig_p010_8.png] view at source ↗
Figure 10
Figure 10. Figure 10: Scale distribution comparison of CAMotion and MoCA-Mask. Frame HGINet ZoomNeXt GT Frame HGINet ZoomNeXt T=235 T=240 T=245 T=50 T=55 T=75 T=80 GT (a) Uncertainty Edge (b) Occlusion (c) Shape Complexity (d) Out-of-View T=175 T=205 T=215 T=225 T=235 T=245 T=255 [PITH_FULL_IMAGE:figures/full_fig_p010_10.png] view at source ↗
Figure 12
Figure 12. Figure 12: Detailed classification of the total frame count across different species. Please zoom in for details. [PITH_FULL_IMAGE:figures/full_fig_p016_12.png] view at source ↗
Figure 13
Figure 13. Figure 13: Examples of our CAMotion dataset with corresponding pixel-level annotations, optical flow and depth map. Each [PITH_FULL_IMAGE:figures/full_fig_p017_13.png] view at source ↗
Figure 14
Figure 14. Figure 14: Visualization of the challenging attributes in CAMotion. Best viewed in color and zoom in for details. [PITH_FULL_IMAGE:figures/full_fig_p018_14.png] view at source ↗
Figure 15
Figure 15. Figure 15: Examples of fine-tuning initial annotations. The white color denotes unchanged areas, while the red and green [PITH_FULL_IMAGE:figures/full_fig_p019_15.png] view at source ↗
Figure 16
Figure 16. Figure 16: Visualization of the bounding box annotations in CAMotion. Best viewed in color and zoom in for details. [PITH_FULL_IMAGE:figures/full_fig_p019_16.png] view at source ↗
Figure 17
Figure 17. Figure 17: Visual comparison with state-of-the-art methods on CAMotion. Please zoom in for details. [PITH_FULL_IMAGE:figures/full_fig_p020_17.png] view at source ↗
Figure 18
Figure 18. Figure 18: Visualization of SOTA method performances on [PITH_FULL_IMAGE:figures/full_fig_p021_18.png] view at source ↗
Figure 20
Figure 20. Figure 20: Failure cases on both HGINet and ZoomNeXt. Please zoom in for details. [PITH_FULL_IMAGE:figures/full_fig_p021_20.png] view at source ↗
read the original abstract

Discovering camouflaged objects is a challenging task in computer vision due to the high similarity between camouflaged objects and their surroundings. While the problem of camouflaged object detection over sequential video frames has received increasing attention, the scale and diversity of existing video camouflaged object detection (VCOD) datasets are greatly limited, which hinders the deeper analysis and broader evaluation of recent deep learning-based algorithms with data-hungry training strategy. To break this bottleneck, in this paper, we construct CAMotion, a high-quality benchmark covers a wide range of species for camouflaged moving object detection in the wild. CAMotion comprises various sequences with multiple challenging attributes such as uncertain edge, occlusion, motion blur, and shape complexity, etc. The sequence annotation details and statistical distribution are presented from various perspectives, allowing CAMotion to provide in-depth analyses on the camouflaged object's motion characteristics in different challenging scenarios. Additionally, we conduct a comprehensive evaluation of existing SOTA models on CAMotion, and discuss the major challenges in VCOD task. The benchmark is available at https://www.camotion.focuslab.net.cn, we hope that our CAMotion can lead to further advancements in the research community.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

0 major / 2 minor

Summary. The manuscript introduces CAMotion, a new benchmark dataset for video camouflaged object detection (VCOD) comprising diverse video sequences across a wide range of species in the wild. It incorporates multiple challenging attributes such as uncertain edges, occlusion, motion blur, and shape complexity, provides detailed sequence annotations and statistical distributions analyzed from various perspectives to support in-depth motion characteristic studies, and includes a comprehensive evaluation of existing state-of-the-art models along with discussion of major VCOD challenges. The benchmark is made publicly available.

Significance. If the claims regarding dataset quality, diversity, and evaluation hold, this contribution is significant because existing VCOD datasets are limited in scale and diversity, impeding deeper analyses and broader testing of data-intensive deep learning methods. The provision of attribute-annotated sequences, multi-perspective statistics on camouflaged object motion, and SOTA model benchmarks directly addresses this gap and can drive further progress in the field. The public release with a dedicated website is a clear strength that supports reproducibility and community use.

minor comments (2)
  1. [Abstract] Abstract: The description of the benchmark's scale (e.g., number of sequences, total frames, or species covered) is stated qualitatively; adding one or two concrete figures here would immediately convey the improvement over prior VCOD datasets.
  2. [Experiments] The evaluation section would benefit from explicit cross-references between the attribute statistics (e.g., frequency of occlusion or motion blur) and the per-attribute performance breakdowns of the tested models.

Simulated Author's Rebuttal

0 responses · 0 unresolved

We thank the referee for the positive summary of our work and the recommendation for minor revision. We are glad that the significance of the CAMotion benchmark for video camouflaged object detection is recognized, particularly regarding its scale, diversity, attribute annotations, and public availability.

Circularity Check

0 steps flagged

No significant circularity

full rationale

The paper introduces CAMotion, a new video dataset for camouflaged moving object detection. Its central contribution is the external collection, annotation, and statistical characterization of real-world sequences, with no equations, derivations, fitted parameters, or predictive modeling present. No self-definitional steps, fitted-input predictions, or load-bearing self-citation chains exist; the benchmark's value rests on independent data curation rather than any internal reduction to its own inputs. This is a standard non-circular dataset release.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 0 invented entities

The work is a data contribution with no mathematical derivations, fitted parameters, or new postulated entities. It rests on the domain assumption that existing VCOD datasets are limited.

axioms (1)
  • domain assumption Existing VCOD datasets are greatly limited in scale and diversity, hindering deeper analysis of deep learning algorithms.
    Explicitly stated in the abstract as the motivation for creating CAMotion.

pith-pipeline@v0.9.0 · 5523 in / 1154 out tokens · 29977 ms · 2026-05-10T18:34:37.040744+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Lean theorems connected to this paper

Citations machine-checked in the Pith Canon. Every link opens the source theorem in the public Lean library.

What do these tags mean?
matches
The paper's claim is directly supported by a theorem in the formal canon.
supports
The theorem supports part of the paper's argument, but the paper may add assumptions or extra steps.
extends
The paper goes beyond the formal theorem; the theorem is a base layer rather than the whole result.
uses
The paper appears to rely on the theorem as machinery.
contradicts
The paper's claim conflicts with a theorem or certificate in the canon.
unclear
Pith found a possible connection, but the passage is too broad, indirect, or ambiguous to say the theorem truly supports the claim.

Reference graph

Works this paper leans on

96 extracted references · 1 canonical work pages

  1. [1]

    explicitly handles motion cues via a frozen pre-trained optical flow fundamental model. VSCode [ 51] and VSCode- v2 [ 52] propose generalist models for multimodal binary segmentation tasks, taking RGB image and optical flow as input to perform frame-by-frame camouflaged object discovery across videos. With the emergence of visual foundation models, severa...

  2. [2]

    further leverages the strong generalizability in natural videos of SAM2 [ 57] to address the VCOD task. However, due to the limitation posed by the low diversity of MoCA- Mask, most VCOD methods require pre-training on image datasets, e.g., COD10K, and more importantly, this constraint impedes the further advancement of this task. 2.3 Motion Segmentation ...

  3. [3]

    [ 65] leverages SAM to capture motion cues from optical flow, and uses the flow as input prompts

    introduce an appearance-based refinement method that leverages temporal consistency in video streams to correct inaccurate flow-based proposals. [ 65] leverages SAM to capture motion cues from optical flow, and uses the flow as input prompts. Besides, [ 66] takes as input the volume of consecutive optical flow fields, and delivers a volume of segments of ...

    2015

  4. [4]

    Self” refers to training and testing on the same dataset (same as diagonal), and “Mean Others

    Due to the variations of network architecture, input resolutions, modalities, as well as pre-processing techniques, we make the best effort to ensure a fair comparison on both datasets. Regarding CAMotion, we surprisingly observe that the image-level COD method HGINet [82] achieves SOTA on JOURNAL OF LATEX CLASS FILES, VOL. 14, NO. 8, AUGUST 2015 7 TABLE ...

    work page arXiv 2015

  5. [5]

    Mean Others

    and Depth Anything V2 [87] to estimate optical flow and depth map, respectively, with the results visualized in Fig. 7. In the cases ofchequered sengi,clownfishandwillow warbler, we observe that the optical flow provides informative partial camouflage cues in moving object scenarios, while the depth map can also reveal camouflaged object contours to some ...

    2015

  6. [6]

    and EMIP [ 50] in eight challenging attributes in terms of Sα and mIoU, see Fig. 8. Notably, we observe that the sequences involving small object (SO), uncertainty edge (UE), occlusion (OC) and multiple objects (MO) are significantly more difficult. In contrast, sequences characterized by shape complexity and motion blur tend to yield relatively better pe...

    2015

  7. [7]

    Nguyen, Zhongliang Nie, Minh- Triet Tran, and Akihiro Sugimoto

    Trung-Nghia Le, Tam V . Nguyen, Zhongliang Nie, Minh- Triet Tran, and Akihiro Sugimoto. Anabranch network for camouflaged object segmentation.Computer Vision and Image Understanding, 184:45–56, 2019

    2019

  8. [8]

    Animal camouflage analysis: Chameleon database

    Przemysław Skurowski, Hassan Abdulameer, Jakub Błaszczyk, Tomasz Depta, Adam Kornacki, and Prze- mysław Kozieł. Animal camouflage analysis: Chameleon database. 2018

    2018

  9. [9]

    Camouflaged object detec- tion

    Deng-Ping Fan, Ge-Peng Ji, Guolei Sun, Ming-Ming Cheng, Jianbing Shen, and Ling Shao. Camouflaged object detec- tion. InIEEE Conference on Computer Vision and Pattern Recognition, pages 2774–2784, 2020

    2020

  10. [10]

    Simultaneously localize, segment and rank the camouflaged objects

    Yunqiu Lv, Jing Zhang, Yuchao Dai, Aixuan Li, Bowen Liu, Nick Barnes, and Deng-Ping Fan. Simultaneously localize, segment and rank the camouflaged objects. In IEEE Conference on Computer Vision and Pattern Recognition, pages 11591–11601, 2021

    2021

  11. [11]

    Learned-Miller

    Pia Bideau and Erik G. Learned-Miller. It’s moving! A probabilistic model for causal motion segmentation in moving camera videos. InEuropean Conference on Computer Vision, pages 433–449, 2016

    2016

  12. [12]

    Implicit motion handling for video camouflaged object detection

    Xuelian Cheng, Huan Xiong, Deng-Ping Fan, Yiran Zhong, Mehrtash Harandi, Tom Drummond, and Zongyuan Ge. Implicit motion handling for video camouflaged object detection. InIEEE Conference on Computer Vision and Pattern Recognition, pages 13854–13863, 2022

    2022

  13. [13]

    Betrayed by motion: Camouflaged object discovery via motion segmentation

    Hala Lamdouar, Charig Yang, Weidi Xie, and Andrew Zisserman. Betrayed by motion: Camouflaged object discovery via motion segmentation. InAsian Conference on Computer Vision, pages 488–503, 2020

    2020

  14. [14]

    Trung-Nghia Le, Yubo Cao, Tan-Cong Nguyen, Minh-Quan Le, Khanh-Duy Nguyen, Thanh-Toan Do, Minh-Triet Tran, and Tam V . Nguyen. Camouflaged instance segmentation in-the-wild: Dataset, method, and benchmark suite.IEEE Transactions on Image Processing, 31:287–300, 2022

    2022

  15. [15]

    Context-aware cross-level fusion network for camouflaged object detection

    Yujia Sun, Geng Chen, Tao Zhou, Yi Zhang, and Nian Liu. Context-aware cross-level fusion network for camouflaged object detection. InInternational Joint Conference on Artificial Intelligence, pages 1025–1031, 2021

    2021

  16. [16]

    Preynet: Preying on cam- ouflaged objects

    Miao Zhang, Shuang Xu, Yongri Piao, Dongxiang Shi, Shusen Lin, and Huchuan Lu. Preynet: Preying on cam- ouflaged objects. InProceedings of the ACM International Conference on Multimedia, pages 5323–5332, 2022

    2022

  17. [17]

    ZoomNeXt: A unified collaborative pyramid network for camouflaged object detection.IEEE Transactions on Pattern Analysis and Machine Intelligence, 46:9205–9220, 2024

    Youwei Pang, Xiaoqi Zhao, Tian-Zhu Xiang, Lihe Zhang, and Huchuan Lu. ZoomNeXt: A unified collaborative pyramid network for camouflaged object detection.IEEE Transactions on Pattern Analysis and Machine Intelligence, 46:9205–9220, 2024

    2024

  18. [18]

    Camouflaged object detection with adaptive partition and background retrieval

    Bowen Yin, Xuying Zhang, Li Liu, Ming-Ming Cheng, Yongxiang Liu, and Qibin Hou. Camouflaged object detection with adaptive partition and background retrieval. International Journal of Computer Vision, 133:4877–4893, 2025

    2025

  19. [19]

    Zoom in and out: A mixed-scale triplet network for camouflaged object detection

    Youwei Pang, Xiaoqi Zhao, Tian-Zhu Xiang, Lihe Zhang, and Huchuan Lu. Zoom in and out: A mixed-scale triplet network for camouflaged object detection. InIEEE Conference on Computer Vision and Pattern Recognition, pages 2150–2160, 2022

    2022

  20. [20]

    Uncertainty-aware joint salient object and camouflaged object detection

    Aixuan Li, Jing Zhang, Yunqiu Lv, Bowen Liu, Tong Zhang, and Yuchao Dai. Uncertainty-aware joint salient object and camouflaged object detection. InIEEE Conference on Computer Vision and Pattern Recognition, pages 10071–10081, 2021

    2021

  21. [21]

    Mutual graph learning for camouflaged object detection

    Qiang Zhai, Xin Li, Fan Yang, Chenglizhao Chen, Hong Cheng, and Deng-Ping Fan. Mutual graph learning for camouflaged object detection. InIEEE Conference on Computer Vision and Pattern Recognition, pages 12997–13007, 2021

    2021

  22. [22]

    Findnet: Can you find me? boundary-and-texture enhancement network for cam- ouflaged object detection.IEEE Transactions on Image Processing, 31:6396–6411, 2022

    Peng Li, Xuefeng Yan, Hongwei Zhu, Mingqiang Wei, Xiao-Ping Zhang, and Jing Qin. Findnet: Can you find me? boundary-and-texture enhancement network for cam- ouflaged object detection.IEEE Transactions on Image Processing, 31:6396–6411, 2022

    2022

  23. [23]

    Camouflaged object detection with feature decomposition and edge reconstruction

    Chunming He, Kai Li, Yachao Zhang, Longxiang Tang, Yulun Zhang, Zhenhua Guo, and Xiu Li. Camouflaged object detection with feature decomposition and edge reconstruction. InIEEE Conference on Computer Vision and Pattern Recognition, pages 22046–22055, 2023

    2023

  24. [24]

    Strategic preys make acute predators: Enhancing camouflaged object detectors by generating camouflaged objects

    Chunming He, Kai Li, Yachao Zhang, Yulun Zhang, Zhen- hua Guo, Xiu Li, Martin Danelljan, and Fisher Yu. Strategic preys make acute predators: Enhancing camouflaged object detectors by generating camouflaged objects. InInterna- tional Conference on Learning Representations, 2024

    2024

  25. [25]

    Nowhere to disguise: Spot camouflaged objects via saliency attribute transfer.IEEE Transactions on Image Processing, 32:3108–3120, 2023

    Wenda Zhao, Shigeng Xie, Fan Zhao, You He, and Huchuan Lu. Nowhere to disguise: Spot camouflaged objects via saliency attribute transfer.IEEE Transactions on Image Processing, 32:3108–3120, 2023

    2023

  26. [26]

    Feature aggregation and propagation network for cam- ouflaged object detection.IEEE Transactions on Image JOURNAL OF LATEX CLASS FILES, VOL

    Tao Zhou, Yi Zhou, Chen Gong, Jian Yang, and Yu Zhang. Feature aggregation and propagation network for cam- ouflaged object detection.IEEE Transactions on Image JOURNAL OF LATEX CLASS FILES, VOL. 14, NO. 8, AUGUST 2015 12 Processing, 31:7036–7047, 2022

    2015

  27. [27]

    A simple yet effective network based on vision transformer for camouflaged object and salient object detection.IEEE Transactions on Image Processing, 34:608–622, 2025

    Chao Hao, Zitong Yu, Xin Liu, Jun Xu, Huanjing Yue, and Jing-Yu Yang. A simple yet effective network based on vision transformer for camouflaged object and salient object detection.IEEE Transactions on Image Processing, 34:608–622, 2025

    2025

  28. [28]

    Escnet:edge-semantic collaborative network for camouflaged object detection

    Sheng Ye, Xin Chen, Yan Zhang, Xianming Lin, and Liujuan Cao. Escnet:edge-semantic collaborative network for camouflaged object detection. InIEEE International Conference on Computer Vision, pages 20053–20063, 2025

    2025

  29. [29]

    Predictive uncertainty estimation for camouflaged object detection.IEEE Transactions on Image Processing, 32:3580–3591, 2023

    Yi Zhang, Jing Zhang, Wassim Hamidouche, and Olivier Dé- forges. Predictive uncertainty estimation for camouflaged object detection.IEEE Transactions on Image Processing, 32:3580–3591, 2023

    2023

  30. [30]

    Detecting camouflaged object in frequency domain

    Yijie Zhong, Bo Li, Lv Tang, Senyun Kuang, Shuang Wu, and Shouhong Ding. Detecting camouflaged object in frequency domain. InIEEE Conference on Computer Vision and Pattern Recognition, pages 4494–4503, 2022

    2022

  31. [31]

    Frequency-spatial entanglement learning for camouflaged object detection

    Yanguang Sun, Chunyan Xu, Jian Yang, Hanyu Xuan, and Lei Luo. Frequency-spatial entanglement learning for camouflaged object detection. InEuropean Conference on Computer Vision, pages 343–360, 2024

    2024

  32. [32]

    Huntnet: Homomorphic unified nexus topol- ogy for camouflaged object detection.IEEE Transactions on Image Processing, 34:6068–6082, 2025

    Haolin Ji, Fengying Xie, Linpeng Pan, Yushan Zheng, and Zhenwei Shi. Huntnet: Homomorphic unified nexus topol- ogy for camouflaged object detection.IEEE Transactions on Image Processing, 34:6068–6082, 2025

    2025

  33. [33]

    Source-free depth for object pop-out

    Zongwei Wu, Danda Pani Paudel, Deng-Ping Fan, Jingjing Wang, Shuo Wang, Cédric Demonceaux, Radu Timofte, and Luc Van Gool. Source-free depth for object pop-out. InIEEE International Conference on Computer Vision, pages 1032–1042, 2023

    2023

  34. [34]

    Improving sam for camouflaged object detection via dual stream adapters

    Jiaming Liu, Linghe Kong, and Guihai Chen. Improving sam for camouflaged object detection via dual stream adapters. InIEEE International Conference on Computer Vision, pages 21906–21916, 2025

    2025

  35. [35]

    Focusdiffuser: Perceiving local disparities for camouflaged object detection

    Jianwei Zhao, Xin Li, Fan Yang, Qiang Zhai, Ao Luo, Zicheng Jiao, and Hong Cheng. Focusdiffuser: Perceiving local disparities for camouflaged object detection. In European Conference on Computer Vision, pages 181–198, 2024

    2024

  36. [36]

    Conditional diffusion models for camouflaged and salient object detection.IEEE Transactions on Pattern Analysis and Machine Intelligence, 47:2833–2848, 2025

    Ke Sun, Zhongxi Chen, Xianming Lin, Xiaoshuai Sun, Hong Liu, and Rongrong Ji. Conditional diffusion models for camouflaged and salient object detection.IEEE Transactions on Pattern Analysis and Machine Intelligence, 47:2833–2848, 2025

    2025

  37. [37]

    Continuous feature representation for camouflaged object detection.IEEE Transactions on Image Processing, 34:5672–5685, 2025

    Ze Song, Xudong Kang, Xiaohui Wei, Jinyang Liu, Zheng Lin, and Shutao Li. Continuous feature representation for camouflaged object detection.IEEE Transactions on Image Processing, 34:5672–5685, 2025

    2025

  38. [38]

    Controllable-lpmoe: Adapting to challenging object seg- mentation via dynamic local priors from mixture-of-experts

    Yanguang Sun, Jiawei Lian, Jian Yang, and Lei Luo. Controllable-lpmoe: Adapting to challenging object seg- mentation via dynamic local priors from mixture-of-experts. InIEEE International Conference on Computer Vision, pages 22327–22337, 2025

    2025

  39. [39]

    Ruozhen He, Qihua Dong, Jiaying Lin, and Rynson W. H. Lau. Weakly-supervised camouflaged object detection with scribble annotations. InProceedings of the AAAI Conference on Artificial Intelligence, pages 781–789, 2023

    2023

  40. [40]

    Weakly- supervised concealed object segmentation with sam-based pseudo labeling and multi-scale feature grouping

    Chunming He, Kai Li, Yachao Zhang, Guoxia Xu, Longxi- ang Tang, Yulun Zhang, Zhenhua Guo, and Xiu Li. Weakly- supervised concealed object segmentation with sam-based pseudo labeling and multi-scale feature grouping. In Advances in Neural Information Processing Systems, 2023

    2023

  41. [41]

    SAM-COD: sam-guided unified framework for weakly- supervised camouflaged object detection

    Huafeng Chen, Pengxu Wei, Guangqian Guo, and Shan Gao. SAM-COD: sam-guided unified framework for weakly- supervised camouflaged object detection. InEuropean Conference on Computer Vision, pages 315–331, 2024

    2024

  42. [42]

    Segment concealed objects with incomplete supervision.IEEE Transactions on Pattern Analysis and Machine Intelligence, 47:7832–7851, 2025

    Chunming He, Kai Li, Yachao Zhang, Ziyun Yang, Youwei Pang, Longxiang Tang, Chengyu Fang, Yulun Zhang, Linghe Kong, Xiu Li, and Sina Farsiu. Segment concealed objects with incomplete supervision.IEEE Transactions on Pattern Analysis and Machine Intelligence, 47:7832–7851, 2025

    2025

  43. [43]

    Just a hint: Point-supervised camouflaged object detection

    Huafeng Chen, Dian Shao, Guangqian Guo, and Shan Gao. Just a hint: Point-supervised camouflaged object detection. InEuropean Conference on Computer Vision, pages 332–348, 2024

    2024

  44. [44]

    Learning camouflaged object detection from noisy pseudo label

    Jin Zhang, Ruiheng Zhang, Yanjiao Shi, Zhe Cao, Nian Liu, and Fahad Shahbaz Khan. Learning camouflaged object detection from noisy pseudo label. InEuropean Conference on Computer Vision, pages 158–174, 2024

    2024

  45. [45]

    Camoteacher: Dual-rotation consistency learning for semi-supervised camouflaged object detection

    Xunfa Lai, Zhiyu Yang, Jie Hu, Shengchuan Zhang, Liujuan Cao, Guannan Jiang, Zhiyu Wang, Songan Zhang, and Rongrong Ji. Camoteacher: Dual-rotation consistency learning for semi-supervised camouflaged object detection. InEuropean Conference on Computer Vision, pages 438–455, 2024

    2024

  46. [46]

    UCOD-DPL: unsupervised camouflaged object detection via dynamic pseudo-label learning

    Weiqi Yan, Lvhai Chen, Huaijia Kou, Shengchuan Zhang, Yan Zhang, and Liujuan Cao. UCOD-DPL: unsupervised camouflaged object detection via dynamic pseudo-label learning. InIEEE Conference on Computer Vision and Pattern Recognition, pages 30365–30375, 2025

    2025

  47. [47]

    Shift the lens: Environment-aware unsupervised camouflaged object de- tection

    Ji Du, Fangwei Hao, Mingyang Yu, Desheng Kong, Jiesheng Wu, Bin Wang, Jing Xu, and Ping Li. Shift the lens: Environment-aware unsupervised camouflaged object de- tection. InIEEE Conference on Computer Vision and Pattern Recognition, pages 19271–19282, 2025

    2025

  48. [48]

    Beyond single images: Retrieval self-augmented unsupervised cam- ouflaged object detection

    Ji Du, Xin Wang, Fangwei Hao, Mingyang Yu, Chunyuan Chen, Jiesheng Wu, Bin Wang, Jing Xu, and Ping Li. Beyond single images: Retrieval self-augmented unsupervised cam- ouflaged object detection. InIEEE International Conference on Computer Vision, pages 22131–22142, 2025

    2025

  49. [49]

    Zero-shot camouflaged object detection.IEEE Transactions on Image Processing, 32:5126– 5137, 2023

    Haoran Li, Chun-Mei Feng, Yong Xu, Tao Zhou, Lina Yao, and Xiaojun Chang. Zero-shot camouflaged object detection.IEEE Transactions on Image Processing, 32:5126– 5137, 2023

    2023

  50. [50]

    Upgen: Unleashing potential of foundation models for training- free camouflage detection via generative models.IEEE Transactions on Image Processing, 34:5400–5413, 2025

    Ji Du, Jiesheng Wu, Desheng Kong, Weiyun Liang, Fangwei Hao, Jing Xu, Bin Wang, Guiling Wang, and Ping Li. Upgen: Unleashing potential of foundation models for training- free camouflage detection via generative models.IEEE Transactions on Image Processing, 34:5400–5413, 2025

    2025

  51. [51]

    Towards real zero-shot camouflaged object segmentation without camouflaged annotations

    Cheng Lei, Jie Fan, Xinran Li, Tian-Zhu Xiang, Ao Li, Ce Zhu, and Le Zhang. Towards real zero-shot camouflaged object segmentation without camouflaged annotations. IEEE Transactions on Pattern Analysis and Machine Intelligence, 47:11990–12004, 2025

    2025

  52. [52]

    Self-supervised video object segmentation by motion grouping

    Charig Yang, Hala Lamdouar, Erika Lu, Andrew Zisserman, and Weidi Xie. Self-supervised video object segmentation by motion grouping. InIEEE International Conference on Computer Vision, pages 7157–7168, 2021

    2021

  53. [53]

    Segmenting moving objects via an object-centric layered representation

    Junyu Xie, Weidi Xie, and Andrew Zisserman. Segmenting moving objects via an object-centric layered representation. InAdvances in Neural Information Processing Systems, 2022

    2022

  54. [54]

    EM-Driven unsupervised learning for efficient motion segmentation.IEEE Transactions on Pattern Analysis and Machine Intelligence, 45:4462–4473, 2023

    Etienne Meunier, Anaïs Badoual, and Patrick Bouthemy. EM-Driven unsupervised learning for efficient motion segmentation.IEEE Transactions on Pattern Analysis and Machine Intelligence, 45:4462–4473, 2023

    2023

  55. [55]

    Learned-Miller, Cordelia Schmid, and Karteek Alahari

    Pia Bideau, Erik G. Learned-Miller, Cordelia Schmid, and Karteek Alahari. The right spin: Learning object motion from rotation-compensated flow fields.International Journal of Computer Vision, 132:40–55, 2024

    2024

  56. [56]

    Explicit motion handling and interactive prompting for video camouflaged object detection.IEEE Transactions on Image Processing, 34:2853–2866, 2025

    Xin Zhang, Tao Xiao, Ge-Peng Ji, Xuan Wu, Keren Fu, and Qijun Zhao. Explicit motion handling and interactive prompting for video camouflaged object detection.IEEE Transactions on Image Processing, 34:2853–2866, 2025

    2025

  57. [57]

    Vscode: General visual salient and camouflaged object detection with 2d prompt learning

    Ziyang Luo, Nian Liu, Wangbo Zhao, Xuguang Yang, Dingwen Zhang, Deng-Ping Fan, Fahad Khan, and Junwei Han. Vscode: General visual salient and camouflaged object detection with 2d prompt learning. InIEEE Conference on Computer Vision and Pattern Recognition, pages 17169–17180, 2024

    2024

  58. [58]

    Ziyang Luo, Nian Liu, Xuguang Yang, Dingwen Zhang, JOURNAL OF LATEX CLASS FILES, VOL. 14, NO. 8, AUGUST 2015 13 Deng-Ping Fan, Fahad Shahbaz Khan, and Junwei Han. Vscode-v2: Dynamic prompt learning for general visual salient and camouflaged object detection with two-stage optimization.IEEE Transactions on Pattern Analysis and Machine Intelligence, 48:3137...

    2015

  59. [59]

    Endow SAM with keen eyes: Temporal-spatial prompt learning for video camouflaged object detection

    Wenjun Hui, Zhenfeng Zhu, Shuai Zheng, and Yao Zhao. Endow SAM with keen eyes: Temporal-spatial prompt learning for video camouflaged object detection. InIEEE Conference on Computer Vision and Pattern Recognition, pages 19058–19067, 2024

    2024

  60. [60]

    SAM-PM: enhancing video cam- ouflaged object detection using spatio-temporal attention

    Muhammad Nawfal Meeran, Gokul Adethya T, and Bhanu Pratyush Mantha. SAM-PM: enhancing video cam- ouflaged object detection using spatio-temporal attention. InIEEE Conference on Computer Vision and Pattern Recognition Workshops, pages 1857–1866, 2024

    2024

  61. [61]

    Berg, Wan-Yen Lo, Piotr Dollár, and Ross B

    Alexander Kirillov, Eric Mintun, Nikhila Ravi, Hanzi Mao, Chloé Rolland, Laura Gustafson, Tete Xiao, Spencer White- head, Alexander C. Berg, Wan-Yen Lo, Piotr Dollár, and Ross B. Girshick. Segment anything. InIEEE International Conference on Computer Vision, pages 3992–4003, 2023

    2023

  62. [62]

    CamSAM2: Segment anything accurately in camouflaged videos

    Yuli Zhou, Yawei Li, Yuqian Fu, Luca Benini, Ender Konukoglu, and Guolei Sun. CamSAM2: Segment anything accurately in camouflaged videos. InAdvances in Neural Information Processing Systems, 2025

    2025

  63. [63]

    Girshick, Piotr Dollár, and Christoph Feichtenhofer

    Nikhila Ravi, Valentin Gabeur, Yuan-Ting Hu, Ronghang Hu, Chaitanya Ryali, Tengyu Ma, Haitham Khedr, Roman Rädle, Chloé Rolland, Laura Gustafson, Eric Mintun, Junt- ing Pan, Kalyan Vasudev Alwala, Nicolas Carion, Chao- Yuan Wu, Ross B. Girshick, Piotr Dollár, and Christoph Feichtenhofer. SAM 2: Segment anything in images and videos. InInternational Confer...

    2025

  64. [64]

    Fast object segmentation in unconstrained video

    Anestis Papazoglou and Vittorio Ferrari. Fast object segmentation in unconstrained video. InIEEE International Conference on Computer Vision, pages 1777–1784, 2013

    2013

  65. [65]

    Motion-guided cascaded refinement network for video object segmentation.IEEE Transactions on Pattern Analysis and Machine Intelligence, 42:1957–1967, 2020

    Ping Hu, Gang Wang, Xiangfei Kong, Jason Kuen, and Yap- Peng Tan. Motion-guided cascaded refinement network for video object segmentation.IEEE Transactions on Pattern Analysis and Machine Intelligence, 42:1957–1967, 2020

    1957

  66. [66]

    Muhammad Faisal, Ijaz Akhter, Mohsen Ali, and Richard I. Hartley. Epo-net: Exploiting geometric constraints on dense trajectories for motion saliency. InIEEE Winter Conference on Applications of Computer Vision, pages 1873–1882, 2020

    2020

  67. [67]

    Joint stereo video deblurring, scene flow estimation and moving object segmentation.IEEE Transactions on Image Processing, 29:1748–1761, 2020

    Liyuan Pan, Yuchao Dai, Miaomiao Liu, Fatih Porikli, and Quan Pan. Joint stereo video deblurring, scene flow estimation and moving object segmentation.IEEE Transactions on Image Processing, 29:1748–1761, 2020

    2020

  68. [68]

    Kankanhalli

    Tao Zhuo, Zhiyong Cheng, Peng Zhang, Yongkang Wong, and Mohan S. Kankanhalli. Unsupervised online video object segmentation with motion property understanding. IEEE Transactions on Image Processing, 29:237–249, 2020

    2020

  69. [69]

    Actor and action modular network for text-based video segmentation.IEEE Transac- tions on Image Processing, 31:4474–4489, 2022

    Jianhua Yang, Yan Huang, Kai Niu, Linjiang Huang, Zhanyu Ma, and Liang Wang. Actor and action modular network for text-based video segmentation.IEEE Transac- tions on Image Processing, 31:4474–4489, 2022

    2022

  70. [70]

    Appearance- based refinement for object-centric motion segmentation

    Junyu Xie, Weidi Xie, and Andrew Zisserman. Appearance- based refinement for object-centric motion segmentation. InEuropean Conference on Computer Vision, pages 238–256, 2024

    2024

  71. [71]

    Moving object segmentation: All you need is SAM (and flow)

    Junyu Xie, Charig Yang, Weidi Xie, and Andrew Zisserman. Moving object segmentation: All you need is SAM (and flow). InAsian Conference on Computer Vision, pages 291–308, 2024

    2024

  72. [72]

    Segmenting the motion components of a video: A long-term unsupervised model.IEEE Transactions on Pattern Analysis and Machine Intelligence, 48:500–511, 2026

    Etienne Meunier and Patrick Bouthemy. Segmenting the motion components of a video: A long-term unsupervised model.IEEE Transactions on Pattern Analysis and Machine Intelligence, 48:500–511, 2026

    2026

  73. [73]

    A general framework for motion segmentation: Independent, articulated, rigid, non-rigid, degenerate and non-degenerate

    Jingyu Yan and Marc Pollefeys. A general framework for motion segmentation: Independent, articulated, rigid, non-rigid, degenerate and non-degenerate. InEuropean Conference on Computer Vision, pages 94–106, 2006

    2006

  74. [74]

    Rao, Roberto Tron, René Vidal, and Yi Ma

    Shankar R. Rao, Roberto Tron, René Vidal, and Yi Ma. Motion segmentation via robust subspace separation in the presence of outlying, incomplete, or corrupted trajec- tories. InIEEE Conference on Computer Vision and Pattern Recognition, 2008

    2008

  75. [75]

    Learning segmentation from point trajec- tories

    Laurynas Karazija, Iro Laina, Christian Rupprecht, and Andrea Vedaldi. Learning segmentation from point trajec- tories. InAdvances in Neural Information Processing Systems, 2024

    2024

  76. [76]

    Cheriyadat and Richard J

    Anil M. Cheriyadat and Richard J. Radke. Non-negative matrix factorization of partial track data for motion seg- mentation. InIEEE International Conference on Computer Vision, pages 865–872, 2009

    2009

  77. [77]

    Motion trajectory segmentation via minimum cost multicuts

    Margret Keuper, Bjoern Andres, and Thomas Brox. Motion trajectory segmentation via minimum cost multicuts. In IEEE International Conference on Computer Vision, pages 3271– 3279, 2015

    2015

  78. [78]

    Higher-order minimum cost lifted mul- ticuts for motion segmentation

    Margret Keuper. Higher-order minimum cost lifted mul- ticuts for motion segmentation. InIEEE International Conference on Computer Vision, pages 4252–4260, 2017

    2017

  79. [79]

    Higher order motion models and spectral clustering

    Peter Ochs and Thomas Brox. Higher order motion models and spectral clustering. InIEEE Conference on Computer Vision and Pattern Recognition, pages 614–621, 2012

    2012

  80. [80]

    Segmentation of moving objects by long term video analysis.IEEE Transactions on Pattern Analysis and Machine Intelligence, 36:1187–1200, 2014

    Peter Ochs, Jitendra Malik, and Thomas Brox. Segmentation of moving objects by long term video analysis.IEEE Transactions on Pattern Analysis and Machine Intelligence, 36:1187–1200, 2014

    2014

Showing first 80 references.