Pith. sign in

REVIEW 1 minor 70 references

MagPlus magnification transforms micro-expressions into signals that standard macro-expression models can process, with de-magnification restoring realistic output.

Reviewed by Pith at T0; open to challenge. T0 means a machine referee read the full paper against a public rubric. the ladder, T0–T4 →

Challenge this review Re-run · record.json Download PDF Read on arXiv ↗

T0 review · grok-4.3

2026-06-27 07:34 UTC pith:GP543FJE

load-bearing objection MagPlus gives a practical magnification pipeline to adapt four off-the-shelf macro models for micro-expressions without retraining, but the reported experiments need concrete metrics to judge the gains.

arxiv 2606.13312 v1 pith:GP543FJE submitted 2026-06-11 cs.CV cs.GR

MagPlus: Bridging Micro-to-Regular Facial Expressions through Learnable Magnification

Sliman Jammal , Andrei Sharf This is my paper
classification cs.CV cs.GR
keywords micro-expressionsfacial expressionsmagnificationfacial animationexpression synthesistransfer learningde-magnification
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved

The pith

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

The paper proposes MagPlus as a pipeline to bridge micro-expressions and regular facial expressions using learnable magnification. Subtle motions are amplified to levels where existing facial animation models can operate on them for synthesis and transfer tasks. After processing, DeMagPlus reduces the intensity back while keeping the motion dynamics. This is evaluated on four pretrained models not trained on micro data, showing more realistic micro-expression generation. The method addresses limited annotated micro data by reusing macro models instead of building new ones.

Core claim

MagPlus learns to magnify subtle facial motions into the range of regular facial expressions, making them compatible with existing facial expression processing models for tasks such as transfer and synthesis; a complementary DeMagPlus module then restores the generated motion back to realistic micro-expression intensity levels while preserving the synthesized dynamics.

What carries the argument

The learnable magnification (MagPlus) and de-magnification (DeMagPlus) modules that scale micro-expression motions up and back down to interface with macro models.

Load-bearing premise

A learnable magnification can transform micro-expressions into signals compatible with existing macro models while preserving the underlying dynamics so that de-magnification yields realistic micro-level output.

What would settle it

An experiment showing that de-magnified outputs fail to match real micro-expression distributions in perceptual studies or motion metrics compared to baselines.

Watch this falsifier — get emailed when new claim-graph text bears on it.

If this is right

  • Pretrained macro-expression models generate more realistic micro-expression motion without retraining.
  • Micro-expression synthesis and transfer become possible using standard facial animation frameworks.
  • The approach works across multiple backbones like FOMM, FSRT, MetaPortrait, and EmoPortraits.
  • New dedicated training on scarce micro-expression data is avoided.

Where Pith is reading between the lines

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

  • Applying the same magnification idea to other weak-signal domains, such as micro body movements, could be tested.
  • Future work might explore whether the magnification is model-agnostic enough to work with any new macro model.
  • Quantitative validation on larger micro-expression datasets would strengthen the preservation of dynamics claim.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit.

Referee Report

0 major / 1 minor

Summary. The manuscript presents MagPlus, a transferable pipeline consisting of a learnable magnification module that scales subtle micro-expression motions into the range of regular (macro) expressions, enabling the direct application of four pretrained macro-expression models (FOMM, FSRT, MetaPortrait, EmoPortraits) without any retraining on micro data. A complementary DeMagPlus module then restores the synthesized motion to realistic micro-expression intensity levels while aiming to preserve the underlying dynamics. The central empirical claim is that this MagPlus-DeMagPlus framework produces more realistic micro-expression output than direct use of the macro backbones.

Significance. If the reported experimental outcomes hold, the approach offers a practical mechanism to leverage abundant macro-expression models and data for the data-scarce micro-expression domain, potentially improving quality, robustness, and generalization in micro-expression synthesis and transfer tasks.

minor comments (1)
  1. [Abstract] Abstract: The summary of experimental results would be strengthened by a brief mention of the datasets used and at least one key quantitative metric (e.g., a specific improvement in a standard metric such as FID or landmark error) to give readers an immediate sense of the magnitude of the claimed gains.

Simulated Author's Rebuttal

0 responses · 0 unresolved

We thank the referee for their thorough reading and positive recommendation to accept the manuscript. The summary accurately captures the core contribution of MagPlus as a transferable pipeline that leverages pretrained macro-expression models without retraining.

Circularity Check

0 steps flagged

No significant circularity; empirical pipeline stands on reported experiments

full rationale

The manuscript describes a learnable magnification pipeline (MagPlus + DeMagPlus) that transforms micro-expression inputs for use by four unmodified pretrained macro-expression models (FOMM, FSRT, MetaPortrait, EmoPortraits), followed by demagnification. The central claim is an empirical one: that this yields more realistic micro-expression output. No equations, fitted parameters renamed as predictions, self-citations invoked as uniqueness theorems, or ansatzes smuggled via prior work appear in the provided description. The derivation chain is absent; the work is self-contained against external benchmarks and does not reduce any result to its own inputs by construction.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

The abstract provides no information on specific parameters, axioms, or new entities introduced.

pith-pipeline@v0.9.1-grok · 5740 in / 1049 out tokens · 23388 ms · 2026-06-27T07:34:43.644261+00:00 · methodology

0 comments
read the original abstract

Facial micro-expressions are subtle and short-lived facial movements that provide important cues about genuine human emotions. However, modeling and generating them remains difficult because annotated micro-expression data is limited and the underlying facial motions are extremely weak. Existing micro-expression generation methods therefore often suffer from limited quality, weak robustness, and poor generalization. We propose MagPlus, a transferable micro-expression processing pipeline that connects micro-expression analysis with standard facial animation models. Instead of training a dedicated generator from scratch, MagPlus learns to magnify subtle facial motions into the range of regular facial expressions, transforming micro-expressions into signals that are compatible with existing facial expression processing models. The magnified sequence is then used by a standard facial expression model for tasks such as transfer and synthesis. A complementary DeMagPlus module then restores the generated motion back to realistic micro-expression intensity levels while preserving the synthesized dynamics. We evaluate the framework using four facial animation models: FOMM, FSRT, MetaPortrait, and EmoPortraits. None of these models are trained on micro-expression data. Experiments show that MagPlus-DeMagPlus enables pretrained macro-expression models to generate more realistic micro-expression motion without retraining the backbones.

Figures

Figures reproduced from arXiv: 2606.13312 by Andrei Sharf, Sliman Jammal.

Figure 1
Figure 1. Figure 1: Two example results. From left to right: source image, MagPlus driver, [PITH_FULL_IMAGE:figures/full_fig_p001_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Pipeline illustration. Left to right: driver micro-expression video input (a), is magnified by MagPlus (b), and then fed together with the source identity [PITH_FULL_IMAGE:figures/full_fig_p003_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Qualitative demonstration of the effect of the MagPlus amplification [PITH_FULL_IMAGE:figures/full_fig_p003_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Four example results. From left to right: source image, MagPlus driver, [PITH_FULL_IMAGE:figures/full_fig_p006_4.png] view at source ↗

discussion (0)

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

Reference graph

Works this paper leans on

70 extracted references · 5 canonical work pages · 1 internal anchor

  1. [1]

    Cross-dimension affinity distillation for 3d em neuron segmentation,

    Nikita Drobyshev and Antoni Bigata Casademunt and Konstantinos Vougioukas and Zoe Landgraf and Stavros Petridis and Maja Pantic , title =. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) , year =. doi:10.1109/CVPR52733.2024.00812 , url =

    work page doi:10.1109/cvpr52733.2024.00812 2024

  2. [2]

    Advances in Neural Information Processing Systems 36 (NeurIPS 2023) , year =

    Zhaoying Pan and Daniel Geng and Andrew Owens , title =. Advances in Neural Information Processing Systems 36 (NeurIPS 2023) , year =

    2023

  3. [3]

    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) , pages=

    Rochow, Andre and Schwarz, Max and Behnke, Sven , title=. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) , pages=

  4. [4]

    Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) , year =

    Hong, Fa-Ting and Zhang, Longhao and Shen, Li and Xu, Dan , title =. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) , year =

  5. [5]

    IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) , year =

    Hong, Fa-Ting and Zhang, Longhao and Shen, Li and Xu, Dan , title =. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) , year =

  6. [6]

    Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) , month =

    Jian Zhao and Hui Zhang , title =. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) , month =. 2022 , pages =

    2022

  7. [7]

    Proceedings of the 29th ACM International Conference on Multimedia , pages =

    Zhang, Yi and Zhao, Youjun and Wen, Yuhang and Tang, Zixuan and Xu, Xinhua and Liu, Mengyuan , title =. Proceedings of the 29th ACM International Conference on Multimedia , pages =. 2021 , isbn =. doi:10.1145/3474085.3479211 , abstract =

    work page doi:10.1145/3474085.3479211 2021

  8. [8]

    Proceedings of the 29th ACM International Conference on Multimedia , series =

    Zhang, Yi and Zhao, Youjun and Wen, Yuhang and Tang, Zixuan and Xu, Xinhua and Liu, Mengyuan , title =. Proceedings of the 29th ACM International Conference on Multimedia , series =. 2021 , pages =

    2021

  9. [9]

    Facial Prior Guided Micro-Expression Generation , year=

    Zhang, Yi and Xu, Xinhua and Zhao, Youjun and Wen, Yuhang and Tang, Zixuan and Liu, Mengyuan , journal=. Facial Prior Guided Micro-Expression Generation , year=

  10. [10]

    Proceedings of the 30th ACM International Conference on Multimedia (ACM MM '22) , address =

    Sirui Zhao and Shukang Yin and Huaying Tang and Rijin Jin and Yifan Xu and Tong Xu and Enhong Chen , title =. Proceedings of the 30th ACM International Conference on Multimedia (ACM MM '22) , address =. 2022 , doi =

    2022

  11. [11]

    Proceedings of the 29th ACM International Conference on Multimedia (ACM MM '21) , address =

    Yifan Xu and Sirui Zhao and Huaying Tang and Xinglong Mao and Tong Xu and Enhong Chen , title =. Proceedings of the 29th ACM International Conference on Multimedia (ACM MM '21) , address =. 2021 , pages =

    2021

  12. [12]

    Proceedings of the 30th ACM International Conference on Multimedia (ACM MM '22) , address =

    Xinqi Fan and Ali Raza Shahid and Hong Yan , title =. Proceedings of the 30th ACM International Conference on Multimedia (ACM MM '22) , address =. 2022 , pages =

    2022

  13. [13]

    Proceedings of the 30th ACM International Conference on Multimedia (ACM MM '22) , address =

    Jun Yu and Guochen Xie and Zhongpeng Cai and Peng He and Fang Gao and Qiang Ling , title =. Proceedings of the 30th ACM International Conference on Multimedia (ACM MM '22) , address =. 2022 , pages =

    2022

  14. [14]

    and Lansley, Cliff and Costen, Nicholas and Tan, Kevin and Yap, Moi Hoon , title =

    Davison, Adrian K. and Lansley, Cliff and Costen, Nicholas and Tan, Kevin and Yap, Moi Hoon , title =. IEEE Transactions on Affective Computing , volume =. 2018 , month = jan, doi =

    2018

  15. [15]

    A Spontaneous Micro-Expression Database: Inducement, Collection and Baseline , booktitle =

    Li, Xiaobai and Pfister, Tomas and Huang, Xiaohua and Zhao, Guoying and Pietik. A Spontaneous Micro-Expression Database: Inducement, Collection and Baseline , booktitle =. 2013 , month = apr, doi =

    2013

  16. [16]

    Liong, Sze-Teng and Gan, Y. S. and See, John and Khor, Huai-Qian and Huang, Yen-Chang , title =. Proceedings of the 2019 14th IEEE International Conference on Automatic Face and Gesture Recognition , series =. 2019 , month = may, doi =

    2019

  17. [17]

    Proceedings of the 2020 15th IEEE International Conference on Automatic Face and Gesture Recognition , series =

    Yap, Chuin Hong and Kendrick, Connah and Yap, Moi Hoon , title =. Proceedings of the 2020 15th IEEE International Conference on Automatic Face and Gesture Recognition , series =. 2020 , doi =

    2020

  18. [18]

    Sophia and Zisserman, Andrew , title =

    Wiles, Olivia and Koepke, A. Sophia and Zisserman, Andrew , title =. Proceedings of the European Conference on Computer Vision (ECCV) , year =

  19. [19]

    Animating Arbitrary Objects via Deep Motion Transfer , booktitle =

    Siarohin, Aliaksandr and Lathuili. Animating Arbitrary Objects via Deep Motion Transfer , booktitle =. 2019 , pages =

    2019

  20. [20]

    First Order Motion Model for Image Animation , booktitle =

    Siarohin, Aliaksandr and Lathuili. First Order Motion Model for Image Animation , booktitle =

  21. [21]

    and Ren, Jian and Chai, Menglei and Tulyakov, Sergey , title =

    Siarohin, Aliaksandr and Woodford, Oliver J. and Ren, Jian and Chai, Menglei and Tulyakov, Sergey , title =. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) , year =

  22. [22]

    Proceedings of the 2020 15th IEEE International Conference on Automatic Face and Gesture Recognition (FG) , year =

    Koujan, Mohammad Rami and Doukas, Michail Christos and Roussos, Anastasios and Zafeiriou, Stefanos , title =. Proceedings of the 2020 15th IEEE International Conference on Automatic Face and Gesture Recognition (FG) , year =

    2020

  23. [23]

    Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) , year =

    Zakharov, Egor and Shysheya, Aliaksandra and Burkov, Egor and Lempitsky, Victor , title =. Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) , year =

  24. [24]

    Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) , year =

    Wang, Ting-Chun and Mallya, Arun and Liu, Ming-Yu , title =. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) , year =

  25. [25]

    and Liu, Shan , title =

    Ren, Yurui and Li, Ge and Chen, Yuanqi and Li, Thomas H. and Liu, Shan , title =. Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) , year =

  26. [26]

    Proceedings of the 30th ACM International Conference on Multimedia , year =

    Drobyshev, Nikita and Chelishev, Jenya and Khakhulin, Taras and Ivakhnenko, Aleksei and Lempitsky, Victor and Zakharov, Egor , title =. Proceedings of the 30th ACM International Conference on Multimedia , year =

  27. [27]

    Proceedings of the 2018 13th IEEE International Conference on Automatic Face and Gesture Recognition (FG) , year =

    Yap, Moi Hoon and See, John and Hong, Xiaopeng and Wang, Su-Jing , title =. Proceedings of the 2018 13th IEEE International Conference on Automatic Face and Gesture Recognition (FG) , year =

    2018

  28. [28]

    and Yap, Moi Hoon , title =

    Merghani, Walied and Davison, Adrian K. and Yap, Moi Hoon , title =. Proceedings of the 2018 13th IEEE International Conference on Automatic Face and Gesture Recognition (FG) , year =

    2018

  29. [29]

    Proceedings of the 2019 14th IEEE International Conference on Automatic Face and Gesture Recognition (FG) , year =

    See, John and Yap, Moi Hoon and Li, Jingting and Hong, Xiaopeng and Wang, Su-Jing , title =. Proceedings of the 2019 14th IEEE International Conference on Automatic Face and Gesture Recognition (FG) , year =

    2019

  30. [30]

    Proceedings of the 2020 15th IEEE International Conference on Automatic Face and Gesture Recognition (FG) , year =

    Li, Jingting and Wang, Su-Jing and Yap, Moi Hoon and See, John and Hong, Xiaopeng and Li, Xiaobai , title =. Proceedings of the 2020 15th IEEE International Conference on Automatic Face and Gesture Recognition (FG) , year =

    2020

  31. [31]

    and Li, Yante and Dong, Zizhao , title =

    Li, Jingting and Yap, Moi Hoon and Cheng, Wen-Huang and See, John and Hong, Xiaopeng and Li, Xiaobai and Wang, Su-Jing and Davison, Adrian K. and Li, Yante and Dong, Zizhao , title =. Proceedings of the 30th ACM International Conference on Multimedia , year =

  32. [32]

    Dynamic Texture Recognition Using Local Binary Patterns with an Application to Facial Expressions , journal =

    Zhao, Guoying and Pietik. Dynamic Texture Recognition Using Local Binary Patterns with an Application to Facial Expressions , journal =. 2007 , doi =

    2007

  33. [33]

    Histograms of Oriented Optical Flow and Binet-Cauchy Kernels on Nonlinear Dynamical Systems for the Recognition of Human Actions , booktitle =

    Chaudhry, Rizwan and Ravichandran, Avinash and Hager, Gregory and Vidal, Ren. Histograms of Oriented Optical Flow and Binet-Cauchy Kernels on Nonlinear Dynamical Systems for the Recognition of Human Actions , booktitle =. 2009 , pages =

    2009

  34. [34]

    Proceedings of the 3rd International Conference on Imaging for Crime Detection and Prevention (ICDP) , year =

    Polikovsky, Senya and Kameda, Yoshinari and Ohta, Yuichi , title =. Proceedings of the 3rd International Conference on Imaging for Crime Detection and Prevention (ICDP) , year =

  35. [35]

    IEEE Transactions on Affective Computing , volume =

    Li, Yante and Wei, Jinsheng and Liu, Yang and Kauttonen, Janne and Zhao, Guoying , title =. IEEE Transactions on Affective Computing , volume =. 2022 , doi =

    2022

  36. [36]

    Journal of Electronic Imaging , volume =

    Xie, Zhihua and Shi, Ling and Cheng, Sijia and Fan, Jiawei and Zhan, Hualin , title =. Journal of Electronic Imaging , volume =. 2022 , doi =

    2022

  37. [37]

    Satish Kumar and Meedimale, Yashwanth Reddy and Mandal, Murari and Vipparthi, Santosh Kumar , title =

    Verma, Monu and Reddy, M. Satish Kumar and Meedimale, Yashwanth Reddy and Mandal, Murari and Vipparthi, Santosh Kumar , title =. IEEE Transactions on Neural Networks and Learning Systems , volume =. 2022 , doi =

    2022

  38. [38]

    IEEE Transactions on Pattern Analysis and Machine Intelligence , volume =

    Li, Jingting and Dong, Zizhao and Lu, Shaoyuan and Wang, Su-Jing and Yan, Wen-Jing and Ma, Yinhuan and Liu, Ye and Huang, Changbing and Fu, Xiaolan , title =. IEEE Transactions on Pattern Analysis and Machine Intelligence , volume =. 2023 , doi =

    2023

  39. [39]

    and Hager, Joseph C

    Ekman, Paul and Friesen, Wallace V. and Hager, Joseph C. , title =. 2002 , isbn =

    2002

  40. [40]

    IEEE Transactions on Affective Computing , volume =

    Varanka, Tuomas and Li, Yante and Peng, Wei and Zhao, Guoying , title =. IEEE Transactions on Affective Computing , volume =. 2024 , doi =

    2024

  41. [41]

    Eulerian Video Magnification for Revealing Subtle Changes in the World , journal =

    Wu, Hao-Yu and Rubinstein, Michael and Shih, Eugene and Guttag, John and Durand, Fr. Eulerian Video Magnification for Revealing Subtle Changes in the World , journal =. 2012 , doi =

    2012

  42. [42]

    Phase-Based Video Motion Processing , journal =

    Wadhwa, Neal and Rubinstein, Michael and Durand, Fr. Phase-Based Video Motion Processing , journal =. 2013 , doi =

    2013

  43. [43]

    Learning-Based Video Motion Magnification , booktitle =

    Oh, Tae-Hyun and Jaroensri, Ronnachai and Kim, Changil and Elgharib, Mohamed and Durand, Fr. Learning-Based Video Motion Magnification , booktitle =. 2018 , pages =

    2018

  44. [44]

    IEEE Transactions on Pattern Analysis and Machine Intelligence , volume =

    Ben, Xianye and Ren, Yi and Zhang, Junping and Wang, Su-Jing and Kpalma, Kidiyo and Meng, Weixiao and Liu, Yong-Jin , title =. IEEE Transactions on Pattern Analysis and Machine Intelligence , volume =

  45. [45]

    IEEE Transactions on Affective Computing , volume =

    Liu, Yong-Jin and Zhang, Jin-Kai and Yan, Wen-Jing and Wang, Su-Jing and Zhao, Guoying and Fu, Xiaolan , title =. IEEE Transactions on Affective Computing , volume =. 2016 , doi =

    2016

  46. [46]

    and Yap, Moi Hoon and Lansley, Cliff , title =

    Davison, Adrian K. and Yap, Moi Hoon and Lansley, Cliff , title =. Proceedings of the 2015 IEEE International Conference on Systems, Man, and Cybernetics , pages =

    2015

  47. [47]

    Signal Processing: Image Communication , volume =

    Gan, Yee Siang and Liong, Sze-Teng and Yau, Wei-Chuen and Huang, Yen-Chang and Tan, Lit-Ken , title =. Signal Processing: Image Communication , volume =

  48. [48]

    Proceedings of the 3rd Workshop on Facial Micro-Expression: Advanced Techniques for Multi-Modal Facial Expression Analysis , pages =

    Guo, Cunhan and Huang, Heyan , title =. Proceedings of the 3rd Workshop on Facial Micro-Expression: Advanced Techniques for Multi-Modal Facial Expression Analysis , pages =

  49. [49]

    Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) , pages =

    Fan, Xinqi and Chen, Xueli and Jiang, Mingjie and Shahid, Ali Raza and Yan, Hong , title =. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) , pages =

  50. [50]

    Proceedings of the Computer Vision and Pattern Recognition Conference , pages =

    Zhang, Bohao and Wang, Xuejiao and Wang, Changbo and He, Gaoqi , title =. Proceedings of the Computer Vision and Pattern Recognition Conference , pages =

  51. [51]

    Proceedings of the 2020 15th IEEE International Conference on Automatic Face and Gesture Recognition , pages =

    Zhang, Li-Wei and Li, Jingting and Wang, Su-Jing and Duan, Xian-Hua and Yan, Wen-Jing and Xie, Hai-Yong and Huang, Shu-Cheng , title =. Proceedings of the 2020 15th IEEE International Conference on Automatic Face and Gesture Recognition , pages =. 2020 , doi =

    2020

  52. [52]

    IEEE Access , volume =

    Zhang, Zhihao and Chen, Tong and Meng, Hongying and Liu, Guangyuan and Fu, Xiaolan , title =. IEEE Access , volume =

  53. [53]

    Spotting Micro-Expressions on Long Videos Sequences , booktitle =

    Li, Jingting and Soladie, Catherine and S. Spotting Micro-Expressions on Long Videos Sequences , booktitle =

  54. [54]

    Signal Processing: Image Communication , volume =

    Liong, Gen-Bing and See, John and Chan, Chee-Seng , title =. Signal Processing: Image Communication , volume =

  55. [55]

    Neurocomputing , volume =

    Liong, Gen-Bing and Liong, Sze-Teng and Chan, Chee Seng and See, John , title =. Neurocomputing , volume =

  56. [56]

    arXiv preprint arXiv:2508.08082 , year =

    Guo, Zizheng and Zou, Bochao and Zhuo, Junbao and Ma, Huimin , title =. arXiv preprint arXiv:2508.08082 , year =

    work page arXiv

  57. [57]

    Proceedings of the 33rd ACM International Conference on Multimedia , series =

    Guo, Zizheng and Zou, Bochao and Jia, Yinuo and Li, Xiangyu and Ma, Huimin , title =. Proceedings of the 33rd ACM International Conference on Multimedia , series =. 2025 , numpages =. doi:10.1145/3746027.3762026 , isbn =

    work page doi:10.1145/3746027.3762026 2025

  58. [58]

    Two-Frame Motion Estimation Based on Polynomial Expansion , booktitle =

    Gunnar Farneb. Two-Frame Motion Estimation Based on Polynomial Expansion , booktitle =. 2003 , pages =

    2003

  59. [59]

    Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition , year =

    Navneet Dalal and Bill Triggs , title =. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition , year =

  60. [60]

    Proceedings of the European Conference on Computer Vision (ECCV) , year =

    Teed, Zachary and Deng, Jia , title =. Proceedings of the European Conference on Computer Vision (ECCV) , year =

  61. [61]

    Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI) , year =

    Ronneberger, Olaf and Fischer, Philipp and Brox, Thomas , title =. Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI) , year =

  62. [62]

    Proceedings of the European Conference on Computer Vision (ECCV) , year =

    Xu, Ning and Yang, Linjie and Fan, Yuchen and Yue, Dingcheng and Liang, Yuchen and Yang, Jianchao and Huang, Thomas , title =. Proceedings of the European Conference on Computer Vision (ECCV) , year =

  63. [63]

    The 2017 DAVIS Challenge on Video Object Segmentation

    Pont-Tuset, Jordi and Perazzi, Federico and Caelles, Sergi and Arbel. The 2017. arXiv preprint arXiv:1704.00675 , year =

    work page internal anchor Pith review Pith/arXiv arXiv 2017

  64. [64]

    , title =

    Xue, Tianfan and Chen, Baian and Wu, Jiajun and Wei, Donglai and Freeman, William T. , title =. International Journal of Computer Vision , volume =. 2019 , doi =

    2019

  65. [65]

    Proceedings of the European Conference on Computer Vision (ECCV) , year =

    Dave, Achal and Khurana, Tarasha and Tokmakov, Pavel and Schmid, Cordelia and Ramanan, Deva , title =. Proceedings of the European Conference on Computer Vision (ECCV) , year =

  66. [66]

    Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) , year =

    Wang, Weiyao and Feiszli, Matt and Wang, Heng and Tran, Du , title =. Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) , year =

  67. [67]

    and Ba, Jimmy , title =

    Kingma, Diederik P. and Ba, Jimmy , title =. Proceedings of the International Conference on Learning Representations (ICLR) , year =

  68. [68]

    Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) , year =

    He, Kaiming and Zhang, Xiangyu and Ren, Shaoqing and Sun, Jian , title =. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) , year =

  69. [69]

    Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) , year =

    Zhang, Bowen and Qi, Chenyang and Zhang, Pan and Zhang, Bo and Wu, HsiangTao and Chen, Dong and Chen, Qifeng and Wang, Yong and Wen, Fang , title =. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) , year =

  70. [70]

    and Merghani, Walied and Yap, Moi Hoon , title =

    Davison, Adrian K. and Merghani, Walied and Yap, Moi Hoon , title =. Journal of Imaging , volume =. 2018 , doi =

    2018