Research behind the predictions
Published research supplies the methods. Each asset keeps its own license.
Credits below describe planned use, not proof that a model has shipped. Code licenses do not automatically cover weights, datasets or paper text. Complete bibliography and BibTeX: CITATIONS.md at the repository root.
| Title / asset | Authors | Institution | Venue / year | Link | License | Glance use |
|---|---|---|---|---|---|---|
| A Model of Saliency-Based Visual Attention for Rapid Scene Analysis | Laurent Itti; Christof Koch; Ernst Niebur | Caltech; additional affiliation TODO-verify | PAMI 1998 | Paper / DOI | Paper/implementation terms TODO-verify | Conceptual saliency and inhibition-of-return background; no original assets bundled. |
| Learning to Predict Where Humans Look / MIT1003 | Tilke Judd; Krista Ehinger; Frédo Durand; Antonio Torralba | MIT; additional affiliation TODO-verify | ICCV 2009 | Paper / DOI | Paper and dataset terms TODO-verify; not mirrored | Historical saliency dataset and prediction reference; no dataset distribution. |
| What do different evaluation metrics tell us about saliency models? | Zoya Bylinskii; Tilke Judd; Aude Oliva; Antonio Torralba; Frédo Durand | MIT | PAMI 2019; arXiv 2016 | Paper / DOI | Paper reuse terms TODO-verify | Metric interpretation; AUC, CC and NSS explanations. |
| DeepGaze IIE: Calibrated prediction in and out-of-domain for state-of-the-art saliency modeling | Akis Linardos; Matthias Kümmerer; Ori Press; Matthias Bethge | University of Tübingen | ICCV 2021 | Paper / DOI | No model redistribution license established in SPEC; user-import only; paper terms TODO-verify | Reference benchmark values only; imported ONNX support subject to verification. |
| Predicting Visual Importance Across Graphic Design Types / UMSI / Imp1k | Camilo Fosco; Vincent Casser; Amish Kumar Bedi; Peter O’Donovan; Aaron Hertzmann; Zoya Bylinskii | MIT + Adobe; full affiliation mapping TODO-verify | UIST 2020 | Paper / DOI | Paper, code, weights and dataset terms TODO-verify | Design-domain importance background; not bundled or claimed as the SUM model. |
| UEyes: An Eye-Tracking Dataset across User Interface Types | Yue Jiang; Luis A. Leiva; Paul R. B. Houssel; Hamed R. Tavakoli; Julia Kylmälä; Antti Oulasvirta | Aalto University; full affiliations TODO-verify | CHI 2023 workshop; arXiv 2024 | Paper / DOI | Paper and dataset terms TODO-verify; not mirrored | UI-domain gaze dataset reference; workshop derivative distinguished from main research paper. |
| EyeFormer: Predicting Personalized Scanpaths with Transformer-Guided Reinforcement Learning | Yue Jiang; Zixin Guo; Hamed R. Tavakoli; Luis A. Leiva; Antti Oulasvirta | Aalto University; University of Luxembourg; Nokia Technologies | UIST 2024 | Paper / DOI | No model license established in SPEC; user-import only; paper terms TODO-verify | Optional UI scanpath import; excluded from redistributed assets. |
| SUM: Saliency Unification through Mamba for Visual Attention Modeling | Alireza Hosseini; Amirhossein Kazerouni; Saeed Akhavan; Michael Brudno; Babak Taati | University of Tehran; University of Toronto; Vector Institute; University Health Network | WACV 2025 | Paper / DOI | MIT code per SPEC; weights/dependencies and paper terms TODO-verify | Candidate image model. ONNX selective-scan export and parity pending; exclude from v1 if unsupported. |
| Unified Image and Video Saliency Modeling / UNISAL | Richard Droste; Jianbo Jiao; J. Alison Noble | University of Oxford | ECCV 2020 | Paper / DOI | Apache-2.0 code per SPEC; weights/dependencies and paper terms TODO-verify | Candidate image/video model; ONNX export and parity pending. |
| TranSalNet: Towards perceptually relevant visual saliency prediction | Lou et al.; full author list TODO-verify | Cardiff University; full affiliations TODO-verify | Neurocomputing 2022 | Paper / DOI | MIT code per SPEC; weights/dependencies and paper terms TODO-verify | Candidate image model; ONNX export and parity pending. |
| CAT2000: A Large Scale Fixation Dataset for Boosting Saliency Research | Ali Borji; Laurent Itti | University of Southern California; affiliation mapping TODO-verify | arXiv 2015 | Paper / DOI | Paper and dataset terms TODO-verify; not mirrored | Benchmark context; dataset linked, never redistributed. |
| MIT/Tübingen Saliency Benchmark / MIT300 | Benchmark contributors; full author attribution TODO-verify | MIT + University of Tübingen | Benchmark website; year TODO-verify | Paper / DOI | Website/data terms TODO-verify; not mirrored | Source for supplied DeepGaze IIE and human reference values. Exact leaderboard row/protocol pending. |
| Saliency Benchmarking Made Easy: Separating Models, Maps and Metrics | Matthias Kümmerer; Thomas S. A. Wallis; Matthias Bethge | University of Tübingen; full affiliations TODO-verify | ECCV 2018 | Paper / DOI | Paper terms TODO-verify | Benchmark protocol background; model density and metric-specific maps differ. |
Redistribution boundary
SUM and TranSalNet have MIT code licenses in SPEC; UNISAL has Apache-2.0. Weight and dependency rights require verification. EyeFormer and DeepGaze IIE remain user-import only under SPEC’s no-license policy. Dataset files are not mirrored.
SUM ONNX export and selective-scan support are unverified. If export cannot pass parity checks, exclude it from v1 and record the outcome in CITATIONS.md.
Questions before you start
Does Glance record my eyes?
No. Glance predicts likely attention from an image. It does not record gaze or use a camera.
Is Glance free?
Glance is a free, open-source desktop app in development. Its own code is MIT; model assets have separate terms.