Human-Computer Interaction · arXiv:2611.17013 v1 · submitted 12 Nov 2026 · 46 references
DiffSSMEye: Conditional High-Frequency Eye Movement Synthesis with Structured State-Space Diffusion
The paper says
“Synthesizing high-frequency eye movements requires preserving long-range temporal dependencies and subject-specific oculomotor dynamics. However, methods based on generative adversarial networks (GANs) and variational autoencoders (VAEs) can struggle to preserve these characteristics simultaneously.”
more of the abstract
We introduce DiffSSMEye, a conditional denoising diffusion probabilistic model with bidirectional Structured State Space Sequence (S4) layers for generating five-second gaze-velocity sequences at 1,000 Hz. Generation is conditioned on a coarse gaze reference, user identity, and task, where identity and task embeddings are incorporated through feature-wise linear modulation. Identity-preservation, multi-resolution spectral, and integrated-drift losses complement noise prediction to constrain biometric consistency, frequency structure, and displacement error. Subject-disjoint evaluation on GazeBase across seven tasks yields mean real–synthetic embedding cosine similarities of 0.91–0.95. DiffSSMEye also achieves the lowest median spatial errors among these baselines for horizontal and random saccade tasks. These results demonstrate improved spatial accuracy and biometric feature consistency for subject-specific gaze synthesis.
from the abstract
Pith says
Machine review · deepseek-v4-flash · 13 Nov 2026 · what was read was not recorded · not checked by a person
It can be wrong. Challenge this review or reply to it.
Holds up, with conditions. Solid spatial results, but the biometric claim is a self-consistency check—authors disclose this, but the abstract doesn't. This line is wrong
3 major objections · 7 minor
How often objections from reviews like this one are right: not yet measured
Not checked: figures, code, what the 46 references say.
The paper says, at §5.3, Eq. (20); §3.5.2, Eq. (12); §3.3, Eq. (3)
The review did not quote this passage.
A classifier read this sentence of the paper as acknowledging the concern (probability 0.94):
“Because EKYT is used for conditioning, supervision, and evaluation, biometric assessment is not independent, and the current metrics do not establish downstream authentication utility or complete physiological fidelity.”
Pith says: Objection 1 of 3 · major
The biometric claim (headline 'biometric feature consistency') rests entirely on EKYT cosine similarity scores (Table 3). However, the same frozen EKYT encoder serves as (i) the conditioning input (Eq. 3), (ii) the identity-preservation loss (Eq. 12), and (iii) the evaluation metric (Eq. 20).
more of objection 1
The paper acknowledges this circularity in Section 7 (b240: 'biometric assessment is not independent'), but the abstract and conclusion state the result without this qualification. The scores therefore measure how well the generator reproduces its own conditioning signal, not independent biometric fidelity. No alternative encoder, downstream authentication task, or cross-dataset identity check is provided. This is a load-bearing issue for the biometric half of the central claim. The spatial accuracy claims are independent and not affected.
The paper says, at Table 1 and Table 2
The review did not quote this passage.
Pith says: Objection 2 of 3 · major
Tables 1 and 2 report U50|E50 and U95|E95 values without any measure of variability (e.g., confidence intervals, standard deviations, or error bars). The statistical analysis in §5.5 (Table 4) provides bootstrap CIs and p-values for RAN RMSE, but the headline spatial accuracy results (U50|E50 for HSS and RAN) lack such quantification.
more of objection 2
Given that the improvement over DiffEyeSyn is modest (3.20 vs 3.73 for HSS; 3.22 vs 4.06 for RAN), it is unclear whether these differences are statistically significant. The authors should provide confidence intervals or significance tests for the median comparisons in Tables 1 and 2.
The paper says, at §5.5, Table 4
The review did not quote this passage.
Pith says: Objection 3 of 3 · major
The statistical analysis uses RMSE over the first 5,000 samples as the metric, which is a different measure from the U50|E50 spatial accuracy reported in Table 1. While the RMSE result supports improved reconstruction accuracy, it does not directly validate the headline spatial accuracy claim (target-alignment error). The authors should clarify how RMSE relates to the U50|E50 metric and whether the significant improvement in RMSE translates to significant improvement in target-alignment error.
7 minor objections
The paper says, at §3.2, Eq. (2)
Pith says: minor objection 1 of 7
The sine normalization uses sin(π v^T / (2 v_max)). The superscript T appears to be a transpose, but v is a vector; please clarify the intended operation (element-wise sine of the scaled vector).
The paper says, at §3.5.4, Eq. (14)
Pith says: minor objection 2 of 7
The drift loss uses L1 norm of the cumulative sum of velocity differences. The notation ||·||_1 is clear, but the equation formatting has extra braces and backslashes that should be cleaned.
show 5 more
The paper says, at §4.3.1, Eq. (16)
Pith says: minor objection 3 of 7
The direction vector formula uses tan(π x/180) etc. This is the standard spherical projection, but the derivation of the normalization factor should be briefly justified or cited.
The paper says, at Table 3
Pith says: minor objection 4 of 7
The standard deviations for DiffSSMEye (e.g., 0.09, 0.11, 0.12) are substantially larger than those for DiffEyeSyn (e.g., 0.04, 0.05, 0.03). This higher variance should be discussed, as it may indicate less consistent biometric alignment across subjects despite higher mean.
The paper says, at §5.6, Table 5
Pith says: minor objection 5 of 7
The ablation study reports EKYT cosine similarity for different conditioning configurations. Since the evaluation metric is the same as the conditioning signal, the ablation results are expected to show improvement when identity conditioning is added. This does not provide independent evidence of biometric fidelity; it only shows that the model uses the conditioning signal. The authors should acknowledge this limitation in the ablation discussion.
The paper says, at §7
Pith says: minor objection 6 of 7
The limitations section is thorough and acknowledges the circularity issue. However, the abstract and conclusion should be revised to qualify the biometric claim accordingly, e.g., 'consistency with the conditioning representation' rather than 'biometric feature consistency'.
The paper says, at General
Pith says: minor objection 7 of 7
The paper uses 'biometric feature consistency' and 'identity preservation' interchangeably. Since the evaluation is not independent, consider using more precise terminology such as 'embedding consistency' or 'conditioning alignment'.
What would settle it
Re-evaluate the 59 held-out subjects using a different, independently trained biometric encoder (e.g., a separate EKYT ensemble trained on a disjoint cohort, or a different architecture like a CNN-based gaze authentication model). If the cosine similarity drops substantially (e.g., below 0.85) or the rank ordering against baselines changes, then the current EKYT-based metric is not a reliable proxy for identity preservation.
from the skeptic's reading
How the review went
4 readings by deepseek-v4-flash · 13 Nov 2026
- Reader holds up, with conditions
- Skeptic agrees
- Editor wrote the verdict above
- Referee major revision: 3 major objections, 7 minor
Not run on this paper: the simulated authors' defence.
Pith did not check this review's objections against the paper.
The review in full
The review in brief, machine-written
Hey,
This paper is a clear step forward for high-frequency gaze synthesis. The spatial accuracy numbers on HSS and RAN are the best I've seen from a learned generator, and the statistical test on RAN RMSE (Holm-adjusted p=0.006 vs DiffEyeSyn) gives me confidence the improvement is real, not just a lucky seed. The architecture is a sensible recombination of published pieces—bidirectional S4 denoiser from SSSD, conditioning from DiffEyeSyn, auxiliary losses from audio—but the configuration for 1,000 Hz gaze is new and the ablation shows identity conditioning is doing the heavy lifting.
Now the soft spot, which the reader and stress-test both caught: the biometric claim. The EKYT encoder is used for conditioning (Eq. 3), identity-preservation loss (Eq. 12), and evaluation (Eq. 20). The paper discloses this in Section 7 (b240: "biometric assessment is not independent"), but the abstract and conclusion state "biometric feature consistency" without that qualification. The 0.91–0.95 cosine similarities therefore measure how well the generator reproduces its own conditioning signal, not independent biometric fidelity. No alternative encoder, downstream authentication task, or cross-dataset check is provided. This doesn't sink the paper—the spatial half is independent and supported—but it means the headline claim is overstated. The authors are honest about the limitation in the text, but they don't neutralize it.
Other concerns are minor: Tables 1 and 2 lack error bars for the median comparisons (though the RAN RMSE test partially addresses this), the two new loss terms (spectral and drift) are never isolated in the ablation, and code/checkpoints are promised rather than shipped. The EKYT training-cohort overlap with test subjects is also unspecified.
Who this is for: researchers working on gaze synthesis or biometric data augmentation. The spatial results are worth engaging with. The biometric claim needs independent verification before being taken at face value.
Recommendation: I'd send this to peer review. The spatial contribution is solid, the architecture is clearly described, and the limitations are honestly stated (even if the abstract oversells). A good reviewer will push for an independent biometric evaluation and error bars on the main tables, but the core work is worth publishing.
The strongest objection
The central claim of "biometric feature consistency" (Abstract, b8) rests on EKYT cosine similarity scores of 0.91–0.95. However, the identical frozen EKYT encoder is used for three distinct roles: (i) conditioning input (Eq. 3), (ii) identity-preservation loss (Eq. 12), and (iii) evaluation metric (Eq. 20). The paper acknowledges this circularity (Section 7, b240: "biometric assessment is not independent"), but the headline claim is stated without this qualification. The scores therefore measure how well the generator reproduces its own conditioning signal, not independent biometric fidelity. No alternative encoder, downstream authentication task, or cross-dataset identity check is provided. The spatial accuracy half of the claim (lowest median target-alignment error on HSS and RAN) is independent of this concern and is supported by the reported tables and statistical tests, though Tables 1 and 2 lack error bars or significance tests for the median comparisons.
The reader's weakest_assumption correctly identifies the circularity of using EKYT for conditioning, loss, and evaluation. The paper's own limitation statement (b240) confirms this. My stress-test agrees that this is the most load-bearing concern because the biometric half of the central claim is not independently validated. The spatial accuracy claim is separate and better supported, though Tables 1 and 2 lack error bars. The concrete test I propose is a straightforward way to settle whether the EKYT similarity scores reflect genuine identity preservation or merely self-consistency. The verdict remains CONDITIONAL because the spatial claim is plausible but the biometric claim requires independent verification before acceptance. I agree with the reader's assessment.
The referee's report
If the spatial accuracy claims hold, DiffSSMEye advances the state of the art in high-frequency gaze synthesis by achieving lower median target-alignment errors than prior generative models (DiffEyeSyn, SP-EyeGAN, VAE) on two saccade tasks. The use of bidirectional S4 layers for temporal modeling in this domain is novel. The paper provides a subject-disjoint evaluation protocol, which is appropriate for assessing generalization to unseen users. The statistical comparison on RAN RMSE (Table 4) with Holm-corrected p-values is a strength. However, the biometric claim is undermined by the circularity of using the same frozen EKYT encoder for conditioning, loss, and evaluation, which the authors acknowledge in Section 7. The spatial accuracy results are independent and supported, but the headline claim of 'biometric feature consistency' is not independently validated.
Pith's reading of the paper (a machine's summary, not the authors')
The paper introduces DiffSSMEye, a conditional denoising diffusion probabilistic model that generates five-second gaze-velocity sequences at 1,000 Hz. It uses bidirectional Structured State Space Sequence (S4) layers in the denoiser, conditioning on a coarse gaze reference, a frozen biometric embedding from the EKYT encoder, and a learned task embedding. The authors argue that this architecture, combined with auxiliary losses for identity preservation, multi-resolution spectral matching, and integrated-drift penalty, produces synthetic eye movements that are more spatially accurate and more consistent with a subject's biometric features than prior GAN, VAE, or diffusion baselines. If true, this would provide a method for generating high-fidelity synthetic gaze data that could supplement limited recordings, support controlled experiments, and reduce privacy risks associated with sharing real eye-tracking data, while retaining subject-specific oculomotor characteristics.
What carries the argument. The key machinery is the denoiser architecture: 30 residual blocks each containing two bidirectional Structured State Space Sequence (S4) layers. These S4 layers model long-range temporal dependencies through a discretized state-space model that is equivalent to a convolution with sequence-spanning kernels, allowing the network to incorporate context from both past and future timesteps. Conditioning is applied via feature-wise linear modulation (FiLM) using the EKYT identity embedding and the task embedding, and a coarse gaze reference is concatenated with the noisy input. The auxiliary losses (identity-preservation via cosine distance in EKYT space, multi-resolution STFT magnitude loss, and integrated-drift penalty) constrain the output beyond the standard noise-prediction objective.
Core claim. The central claim is that DiffSSMEye, by integrating bidirectional S4 layers into a conditional DDPM denoiser and augmenting the noise-prediction loss with identity-preservation, multi-resolution spectral, and integrated-drift objectives, can synthesize five-second, 1000 Hz gaze-velocity sequences that achieve lower median spatial error on horizontal and random saccade tasks and higher real–synthetic embedding cosine similarity on six of seven tasks compared to SP-EyeGAN, a VAE baseline, and DiffEyeSyn. The authors state that these results demonstrate improved spatial accuracy and biometric feature consistency for subject-specific gaze synthesis.
The premise it rests on. The biometric consistency claim depends on the assumption that cosine similarity between real and synthetic EKYT embeddings is a valid measure of identity preservation for unseen subjects, but the EKYT encoder is used for conditioning, supervision, and evaluation, so the metric partly measures self-consistency rather than independent biometric fidelity.
If the paper is right (Pith's inferences, not the authors')
If DiffSSMEye's spatial accuracy and biometric consistency hold across diverse datasets, synthetic gaze could serve as a drop-in replacement for real data in training and evaluating gaze-based interfaces, biometric authentication systems, and clinical assessment tools, reducing the need for expensive and time-consuming data collection.
The method's ability to preserve subject-specific oculomotor dynamics at 1000 Hz suggests that synthetic data could be used to augment small or imbalanced datasets for machine learning models, potentially improving their robustness and fairness across demographic groups.
The framework's conditioning on a coarse reference trajectory and task embedding implies that users could generate gaze sequences for novel task conditions or imagined scenarios by supplying a new coarse reference and task label, enabling controlled experiments that are difficult to conduct with human participants.
The explicit modeling of long-range dependencies via S4 layers may generalize to other high-frequency physiological signals (e.g., ECG, EEG, EMG) where preserving subject-specific temporal structure is critical, offering a template for conditional generation in biometry.
The paper's ablation study shows that identity conditioning provides the largest individual gain in embedding similarity, suggesting that biometric encoders are a powerful conditioning signal for subject-specific generation, but the authors acknowledge that the evaluation metric is not independent of the conditioning signal, so the true identity-preservation capability remains to be verified with
Because the EKYT embedding is used for conditioning, supervision, and evaluation, the headline cosine similarity scores (0.91–0.95) partly measure the generator's ability to reproduce the signal that guides it, not an independent measure of identity preservation. An independent biometric encoder or a downstream authentication task would provide a stronger test of identity fidelity.
The spatial accuracy improvements over DiffEyeSyn are modest (0.53 dva for HSS, 0.84 dva for RAN at U50|E50), and at the 95th percentile DiffEyeSyn actually outperforms DiffSSMEye on RAN. This suggests that the main advantage of the S4 architecture may lie in modeling the central tendency of gaze placement rather than eliminating extreme outliers, and that the choice of evaluation percentile can c
The paper evaluates only on GazeBase, which has a specific sampling rate (1000 Hz), tracker (EyeLink 1000), and task set. Generalization to other trackers, sampling rates (e.g., 120 Hz, 2000 Hz), or clinical populations (e.g., dyslexia, ADHD) is untested, and the model's performance may degrade if the coarse-reference construction or EKYT encoder is not well-matched to the new data.
The integrated-drift loss penalizes endpoint displacement over 5-second windows, which may encourage the model to avoid low-frequency drift at the expense of higher-frequency micro-movements that are characteristic of individual oculomotor signatures. A comparison of power spectral density or microsaccade rates between real and synthetic data would clarify whether spectral fidelity is maintained a
Check this review
Pith stored no record of this review's passes and took no fingerprint of it. Reviews made by code from 13 Nov 2026 on carry both.
How often reviews like this one are right
Reviews like this one: written by deepseek-v4-flash, where what was read was not recorded.
How often objections from reviews like this one are right: not yet measured
Reviews by people
This review was written by a machine. No person has reviewed this paper on Pith yet. A scientist listed on Pith can review it for a fee, and their review is published here whatever it concludes.
The paper
Abstract
Synthesizing high-frequency eye movements requires preserving long-range temporal dependencies and subject-specific oculomotor dynamics. However, methods based on generative adversarial networks (GANs) and variational autoencoders (VAEs) can struggle to preserve these characteristics simultaneously. We introduce DiffSSMEye, a conditional denoising diffusion probabilistic model with bidirectional Structured State Space Sequence (S4) layers for generating five-second gaze-velocity sequences at 1,000 Hz. Generation is conditioned on a coarse gaze reference, user identity, and task, where identity and task embeddings are incorporated through feature-wise linear modulation. Identity-preservation, multi-resolution spectral, and integrated-drift losses complement noise prediction to constrain biometric consistency, frequency structure, and displacement error. Subject-disjoint evaluation on GazeBase across seven tasks yields mean real–synthetic embedding cosine similarities of 0.91–0.95. DiffSSMEye also achieves the lowest median spatial errors among these baselines for horizontal and random saccade tasks. These results demonstrate improved spatial accuracy and biometric feature consistency for subject-specific gaze synthesis.
The paper's own sentences, arranged, kept beside the review and separate from it. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. No sentence in this record was written by a model.
abstract compiled · 2026-11-13
The authors' main claim, as the classifier picked it out 1.00
“These results demonstrate improved spatial accuracy and biometric feature consistency for subject-specific gaze synthesis.”
How the main claim is stated: asserted 1.00
What the abstract itself states, as probabilities: claims first 0.06 · states limitation 0.09 · human participants 0.67 · controlled comparison 0.81 · randomized assignment 0.02 · states quantitative result 0.99 · compares with prior results 0.95 · mentions code or data availability 0.03
The abstract, sentence by sentence
This table labels the abstract only (arXiv listing abstract v1). The number is the probability the classifier gave the label.
| Sentence | Role | The authors' own work | States the main conclusion | Strength |
|---|---|---|---|---|
| Synthesizing high-frequency eye movements requires preserving long-range temporal dependencies and subject-specific oculomotor dynamics. | background 1.00 | 0.07 | 0.03 | asserted 1.00 |
| However, methods based on generative adversarial networks (GANs) and variational autoencoders (VAEs) can struggle to preserve these characteristics simultaneously. | gap 0.72 | 0.07 | 0.02 | hedged possibility 0.96 |
| We introduce DiffSSMEye, a conditional denoising diffusion probabilistic model with bidirectional Structured State Space Sequence (S4) layers for generating five-second gaze-velocity sequences at 1,000 Hz. | method 0.58 | 0.91 | 0.06 | asserted 0.99 |
| Generation is conditioned on a coarse gaze reference, user identity, and task, where identity and task embeddings are incorporated through feature-wise linear modulation. | method 1.00 | 0.87 | 0.03 | asserted 1.00 |
| Identity-preservation, multi-resolution spectral, and integrated-drift losses complement noise prediction to constrain biometric consistency, frequency structure, and displacement error. | method 0.99 | 0.85 | 0.06 | asserted 1.00 |
| Subject-disjoint evaluation on GazeBase across seven tasks yields mean real--synthetic embedding cosine similarities of 0.91--0.95. | result 1.00 | 0.96 | 0.10 | asserted 1.00 |
| DiffSSMEye also achieves the lowest median spatial errors among these baselines for horizontal and random saccade tasks. | result 1.00 | 0.93 | 0.13 | asserted 1.00 |
| These results demonstrate improved spatial accuracy and biometric feature consistency for subject-specific gaze synthesis. | interpretation 1.00 | 0.88 | 0.90 | asserted 1.00 |
What kind of paper the classifier reports this is: method or tool 1.00 · evidence from observation or experiment 0.76
What was examined, and what was not
Sources read
- arXiv listing abstract v1
Not examined
- full text
- figures and tables
- references and citing sentences
- relations to other papers
Levels run
- P abstract
Not run
- S sections
- T body sentences
- C citations
- R cross-paper relations
How the labels were made
Compiled by classifier-1.13.0 via TypeSafe API, question bank abstract-p1-20260923, 2026-11-13: 1 request, 6,270 input tokens.
Every quoted sentence on this record is the authors'. Every label is from Pith's closed vocabulary, with the probability shown beside it. This record as JSON
Figures (2)
References (46)
- [1] Keith Rayner. Eye movements and attention in reading, scene perception, and visual search.The quarterly journal of experimental psychology, 62(8):1457–1506, 2009 on Pith
- [2] Stephen Hutt, Kristina Krasich, James R. Brockmole, and Sidney K. D’Mello. Breaking out of the lab: Mitigating mind wandering with gaze-based attention-aware technology in classrooms. InProceedings of the 2021 CHI conference on human factors in computing systems, pages 1–14, 2021 on Pith
- [3] Raphael Menges, Chandan Kumar, and Steffen Staab. Improving user experience of eye tracking-based interaction: Introspecting and adapting interfaces.ACM Transactions on Computer-Human Interaction (TOCHI), 26(6):1–46, 2019 on Pith
- [4] Dillon Lohr and Oleg V Komogortsev. Eye know you too: Toward viable end-to-end eye movement biometrics for user authentication.IEEE Transactions on Information Forensics and Security, 17:3151–3164, 2022 on Pith
- [5] Anjul Patney, Marco Salvi, Joohwan Kim, Anton Kaplanyan, Chris Wyman, Nir Benty, David Luebke, and Aaron Lefohn. Towards foveated rendering for gaze-tracked virtual reality.ACM Transactions On Graphics (TOG), 35 (6):1–12, 2016 on Pith
- [6] Hardeep Singh, Jagjit Singh Bhatia, and Jasbir Kaur. Eye tracking based driver fatigue monitoring and warning system. InIndia International Conference on Power Electronics 2010 (IICPE2010), pages 1–6. IEEE, 2011 on Pith
- [7] Patrick Haller, Andreas Säuberli, Sarah Elisabeth Kiener, Jinger Pan, Ming Yan, and Lena Jäger. Eye-tracking based classification of mandarin chinese readers with and without dyslexia using neural sequence models.arXiv preprint arXiv:2210.09819, 2022. 12 DiffSSMEye: Conditiona... on PithPith's reviewarXiv
- [8] Tamilvizhi Thanarajan, Youseef Alotaibi, Surendran Rajendran, and Krishnaraj Nagappan. Eye-tracking based autism spectrum disorder diagnosis using chaotic butterfly optimization with deep learning model.Computers, Materials & Continua, 76(2), 2023 on Pith
- [9] Liya Merzon, Kati Pettersson, Eeva T Aronen, Hanna Huhdanpää, Erik Seesjärvi, Linda Henriksson, W Joseph MacInnes, Minna Mannerkoski, Emiliano Macaluso, and Juha Salmi. Eye movement behavior in a real-world virtual reality task reveals adhd in children.Scientific reports, 12(1... on Pith
- [10] SR Research. EyeLink 1000 Plus Technical Specifications. https://www.sr-research.com/ eyelink-1000-plus-technical-specifications/, 2026. Accessed: 2026-10-11 on Pith
- [11] Tobii Pro. Tobii Pro Spectrum. https://www.tobii.com/products/eye-trackers/screen-based/ tobii-pro-spectrum, 2026. Accessed: 2026-10-11 on Pith
- [12] Henry Griffith, Dillon Lohr, Evgeny Abdulin, and Oleg Komogortsev. Gazebase, a large-scale, multi-stimulus, longitudinal eye movement dataset.Scientific Data, 8(1):184, 2021 on Pith
- [13] Julian Steil, Inken Hagestedt, Michael Xuelin Huang, and Andreas Bulling. Privacy-aware eye tracking using differential privacy. InProceedings of the 11th ACM Symposium on Eye Tracking Research & Applications, pages 1–9, 2019 on Pith
- [14] Wolfgang Fuhl, Yao Rong, and Enkelejda Kasneci. Fully convolutional neural networks for raw eye tracking data segmentation, generation, and reconstruction. In2020 25th International Conference on Pattern Recognition (ICPR), pages 142–149. IEEE, 2021 on Pith
- [15] Paul Prasse, David Robert Reich, Silvia Makowski, Seoyoung Ahn, Tobias Scheffer, and Lena A Jäger. Sp-eyegan: Generating synthetic eye movement data with generative adversarial networks. InProceedings of the 2023 symposium on eye tracking research and applications, pages 1–9, 2023 on Pith
- [16] Jonathan Ho, Ajay Jain, and Pieter Abbeel. Denoising diffusion probabilistic models.Advances in neural information processing systems, 33:6840–6851, 2020 on Pith
- [17] Chuhan Jiao, Guanhua Zhang, Yeonjoo Cho, Zhiming Hu, and Andreas Bulling. Diffeyesyn: Diffusion-based user-specific eye movement synthesis.arXiv preprint arXiv:2409.01240, 2024 on PithPith's reviewarXiv
- [18] Albert Gu, Karan Goel, and Christopher Ré. Efficiently modeling long sequences with structured state spaces. arXiv preprint arXiv:2111.00396, 2021 on PithPith's reviewarXiv
- [19] Juan Miguel Lopez Alcaraz and Nils Strodthoff. Diffusion-based time series imputation and forecasting with structured state space models.arXiv preprint arXiv:2208.09399, 2022 on PithPith's reviewarXiv
- [20] Juan Miguel Lopez Alcaraz and Nils Strodthoff. Diffusion-based conditional ecg generation with structured state space models.Computers in biology and medicine, 163:107115, 2023 on Pith
show 26 more
- [21] Ethan Perez, Florian Strub, Harm De Vries, Vincent Dumoulin, and Aaron Courville. Film: Visual reasoning with a general conditioning layer. InProceedings of the AAAI conference on artificial intelligence, volume 32, 2018 on Pith
- [22] Sooha Park Lee, Jeremy B Badler, and Norman I Badler. Eyes alive. InProceedings of the 29th annual conference on Computer graphics and interactive techniques, pages 637–644, 2002 on Pith
- [23] Andrew T Duchowski and Sophie Jörg. Modeling physiologically plausible eye rotations. InProceedings of computer graphics international, 2015 on Pith
- [24] Andrew T Duchowski, Sophie Jörg, Tyler N Allen, Ioannis Giannopoulos, and Krzysztof Krejtz. Eye movement synthesis. InProceedings of the ninth biennial ACM symposium on eye tracking research & applications, pages 147–154, 2016 on Pith
- [25] Xiaohan Ma and Zhigang Deng. Natural eye motion synthesis by modeling gaze-head coupling. In2009 IEEE Virtual Reality Conference, pages 143–150. IEEE, 2009 on Pith
- [26] Wolfgang Fuhl and Enkelejda Kasneci. Eye movement velocity and gaze data generator for evaluation, robustness testing and assess of eye tracking software and visualization tools.arXiv preprint arXiv:1808.09296, 2018 on PithPith's reviewarXiv
- [27] Wolfgang Fuhl, Thiago Santini, Thomas Kuebler, Nora Castner, Wolfgang Rosenstiel, and Enkelejda Kasneci. Eye movement simulation and detector creation to reduce laborious parameter adjustments.arXiv preprint arXiv:1804.00970, 2018 on PithPith's reviewarXiv
- [28] Sang Hoon Yeo, Martin Lesmana, Debanga R Neog, and Dinesh K Pai. Eyecatch: Simulating visuomotor coordination for object interception.ACM Transactions on Graphics (TOG), 31(4):1–10, 2012 on Pith
- [29] Greg Welch, Gary Bishop, et al. An introduction to the kalman filter. 1995. 13 DiffSSMEye: Conditional High-Frequency Eye Movement Synthesis with Structured State-Space Diffusion on Pith
- [30] Daniel J Campbell, Joseph Chang, Katarzyna Chawarska, and Frederick Shic. Saliency-based bayesian modeling of dynamic viewing of static scenes. InProceedings of the symposium on eye tracking research and applications, pages 51–58, 2014 on Pith
- [31] Guohao Lan, Tim Scargill, and Maria Gorlatova. Eyesyn: Psychology-inspired eye movement synthesis for gaze-based activity recognition. In2022 21st ACM/IEEE international conference on information processing in sensor networks (IPSN), pages 233–246. IEEE, 2022 on Pith
- [32] Daniel Simon, Srinivas Sridharan, Shagan Sah, Raymond Ptucha, Chris Kanan, and Reynold Bailey. Automatic scanpath generation with deep recurrent neural networks. InProceedings of the ACM symposium on applied perception, pages 130–130, 2016 on Pith
- [33] Marc Assens, Xavier Giro-i Nieto, Kevin McGuinness, and Noel E O’Connor. Pathgan: Visual scanpath prediction with generative adversarial networks. InProceedings of the European Conference on Computer Vision (ECCV) Workshops, pages 0–0, 2018 on Pith
- [34] Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. Generative adversarial networks.Communications of the ACM, 63(11):139–144, 2020 on Pith
- [35] Celso M De Melo, Antonio Torralba, Leonidas Guibas, James DiCarlo, Rama Chellappa, and Jessica Hodgins. Next-generation deep learning based on simulators and synthetic data.Trends in cognitive sciences, 26(2):174–187, 2022 on Pith
- [36] Wolfgang Fuhl and Enkelejda Kasneci. Hpcgen: Hierarchical k-means clustering and level based principal components for scan path genaration. In2022 Symposium on Eye Tracking Research and Applications, pages 1–7, 2022 on Pith
- [37] Chuhan Jiao, Yao Wang, Guanhua Zhang, Mihai Bâce, Zhiming Hu, and Andreas Bulling. Diffgaze: A diffusion model for modelling fine-grained human gaze behaviour on 360° images.ACM Transactions on Interactive Intelligent Systems, 2025 on Pith
- [38] Zhifeng Kong, Wei Ping, Jiaji Huang, Kexin Zhao, and Bryan Catanzaro. Diffwave: A versatile diffusion model for audio synthesis.arXiv preprint arXiv:2009.09761, 2020 on PithPith's reviewarXiv
- [39] Kamrul Hasan, Dmytro Katrychuk, Mehedi Hasan Raju, and Oleg V Komogortsev. Quantitative and quali- tative comparison of generative models for subject-specific gaze synthesis: Diffusion vs gan.arXiv preprint arXiv:2511.09867, 2025 on PithPith's reviewarXiv
- [40] Mehedi H Raju, Lee Friedman, Troy M Bouman, and Oleg V Komogortsev. Determining which sine wave frequencies correspond to signal and which correspond to noise in eye-tracking time-series.Journal of Eye Movement Research, 14(3):16, 2021 on Pith
- [41] Abraham Savitzky and Marcel JE Golay. Smoothing and differentiation of data by simplified least squares procedures.Analytical chemistry, 36(8):1627–1639, 1964 on Pith
- [42] Albert Gu, Tri Dao, Stefano Ermon, Atri Rudra, and Christopher Ré. Hippo: Recurrent memory with optimal polynomial projections.Advances in neural information processing systems, 33:1474–1487, 2020 on Pith
- [43] Dan Hendrycks and Kevin Gimpel. Gaussian error linear units (gelus).arXiv preprint arXiv:1606.08415, 2016 on PithPith's reviewarXiv
- [44] Ilya Loshchilov and Frank Hutter. Decoupled weight decay regularization.arXiv preprint arXiv:1711.05101, 2017 on PithPith's reviewarXiv
- [45] Dillon J Lohr, Lee Friedman, and Oleg V Komogortsev. Evaluating the data quality of eye tracking signals from a virtual reality system: Case study using smi’s eye-tracking htc vive.arXiv preprint arXiv:1912.02083, 2019 on PithPith's reviewarXiv
- [46] Samantha Aziz, Dillon J Lohr, Lee Friedman, and Oleg Komogortsev. Evaluation of eye tracking signal quality for virtual reality applications: A case study in the meta quest pro. InProceedings of the 2024 Symposium on Eye Tracking Research and Applications, pages 1–8, 2024. 14 on Pith
Challenges and discussion
Disagree with the review, or know something it missed? Leave a comment, or challenge this review formally: a challenge becomes a permanent entry in this paper's record, and its decision is published here.
Come back by email
A short list of the week's newly reviewed papers. Nothing is sent until you confirm from your inbox, and every email has a link that stops it. No account.


No comments yet.
Sign in to comment