{"_id":"6ZYYJwJEtS2PxynxW","bibbaseid":"pather-martignne-bugnet-boutaleb-dhondt-maia-eyetheiaalightweightandaccessibleeyetrackingtoolbox-2027","author_short":["Pather, S.","Martignène, N.","Bugnet, A.","Boutaleb, F.","D’Hondt, F.","Maia, D. S."],"bibdata":{"bibtype":"article","type":"article","abstract":"We introduce EyeTheia, a lightweight and open deep learning pipeline for webcam-based gaze estimation, designed for browser-based experimental platforms and real-world cognitive and clinical research. EyeTheia enables real-time gaze tracking using only a standard laptop webcam, combining MediaPipe-based landmark extraction with a convolutional neural network inspired by iTracker and optional user-specific fine-tuning. We investigate two complementary strategies: adapting a model pretrained on mobile data and training the same architecture from scratch on a desktop-oriented dataset. Validation results on MPIIFaceGaze show comparable performance between both approaches prior to calibration, while lightweight user-specific fine-tuning consistently reduces gaze prediction error. We further evaluate EyeTheia in a realistic Dot-Probe task and compare it to the commercial webcam-based tracker SeeSo SDK. Results indicate strong agreement in left–right gaze allocation during stimulus presentation, despite higher temporal variability. Overall, EyeTheia provides a transparent and extensible solution for low-cost gaze tracking, suitable for scalable and reproducible experimental and clinical studies. The code, trained models, and experimental materials are publicly available (EyeTheia repository and Calypso experimental platform).","author":[{"firstnames":["Stevenson"],"propositions":[],"lastnames":["Pather"],"suffixes":[]},{"firstnames":["Niels"],"propositions":[],"lastnames":["Martignène"],"suffixes":[]},{"firstnames":["Arnaud"],"propositions":[],"lastnames":["Bugnet"],"suffixes":[]},{"firstnames":["Fouad"],"propositions":[],"lastnames":["Boutaleb"],"suffixes":[]},{"firstnames":["Fabien"],"propositions":[],"lastnames":["D’Hondt"],"suffixes":[]},{"firstnames":["Deise","Santana"],"propositions":[],"lastnames":["Maia"],"suffixes":[]}],"doi":"10.1007/978-3-032-31438-3_35/TABLES/3","isbn":"9783032314376","issn":"16113349","journal":"Lecture Notes in Computer Science","keywords":"Cognitive neuroscience,Deep learning,Eye tracking,Gaze estimation,Web-based experimentation","pages":"526-541","publisher":"Springer Science and Business Media Deutschland GmbH","title":"EyeTheia: A Lightweight and Accessible Eye-Tracking Toolbox","volume":"16821 LNCS","url":"https://link.springer.com/chapter/10.1007/978-3-032-31438-3_35","year":"2027","bibtex":"@article{Pather2027,\n abstract = {We introduce EyeTheia, a lightweight and open deep learning pipeline for webcam-based gaze estimation, designed for browser-based experimental platforms and real-world cognitive and clinical research. EyeTheia enables real-time gaze tracking using only a standard laptop webcam, combining MediaPipe-based landmark extraction with a convolutional neural network inspired by iTracker and optional user-specific fine-tuning. We investigate two complementary strategies: adapting a model pretrained on mobile data and training the same architecture from scratch on a desktop-oriented dataset. Validation results on MPIIFaceGaze show comparable performance between both approaches prior to calibration, while lightweight user-specific fine-tuning consistently reduces gaze prediction error. We further evaluate EyeTheia in a realistic Dot-Probe task and compare it to the commercial webcam-based tracker SeeSo SDK. Results indicate strong agreement in left–right gaze allocation during stimulus presentation, despite higher temporal variability. Overall, EyeTheia provides a transparent and extensible solution for low-cost gaze tracking, suitable for scalable and reproducible experimental and clinical studies. The code, trained models, and experimental materials are publicly available (EyeTheia repository and Calypso experimental platform).},\n author = {Stevenson Pather and Niels Martignène and Arnaud Bugnet and Fouad Boutaleb and Fabien D’Hondt and Deise Santana Maia},\n doi = {10.1007/978-3-032-31438-3_35/TABLES/3},\n isbn = {9783032314376},\n issn = {16113349},\n journal = {Lecture Notes in Computer Science},\n keywords = {Cognitive neuroscience,Deep learning,Eye tracking,Gaze estimation,Web-based experimentation},\n pages = {526-541},\n publisher = {Springer Science and Business Media Deutschland GmbH},\n title = {EyeTheia: A Lightweight and Accessible Eye-Tracking Toolbox},\n volume = {16821 LNCS},\n url = {https://link.springer.com/chapter/10.1007/978-3-032-31438-3_35},\n year = {2027}\n}\n","author_short":["Pather, S.","Martignène, N.","Bugnet, A.","Boutaleb, F.","D’Hondt, F.","Maia, D. S."],"key":"Pather2027","id":"Pather2027","bibbaseid":"pather-martignne-bugnet-boutaleb-dhondt-maia-eyetheiaalightweightandaccessibleeyetrackingtoolbox-2027","role":"author","urls":{"Paper":"https://link.springer.com/chapter/10.1007/978-3-032-31438-3_35"},"keyword":["Cognitive neuroscience","Deep learning","Eye tracking","Gaze estimation","Web-based experimentation"],"metadata":{"authorlinks":{}}},"bibtype":"article","biburl":"https://nextcloud.univ-lille.fr/index.php/s/ZN4QZ7dH9iNaNWE/download/Interactions.bib","dataSources":["3GW57JhuLNkW5xJr9","ECsXQHgbAjNJDKiJ7"],"keywords":["cognitive neuroscience","deep learning","eye tracking","gaze estimation","web-based experimentation"],"search_terms":["eyetheia","lightweight","accessible","eye","tracking","toolbox","pather","martignène","bugnet","boutaleb","d’hondt","maia"],"title":"EyeTheia: A Lightweight and Accessible Eye-Tracking Toolbox","year":2027}