{"url":"/task/scanpath-prediction","name":"Scanpath prediction","slug":"scanpath-prediction","description_markdown":"Learning to Predict Sequences of Human Fixations.","categories":[{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":34,"papers_with_code":13,"benchmarks":3,"benchmark_tables_in_archive":3,"benchmark_tables_shown":3,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":2,"subtasks":0,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/scanpath-prediction-on-capmit1003","slug":"scanpath-prediction-on-capmit1003","dataset":"CapMIT1003","dataset_url":"/dataset/capmit1003","rows_in_archive":2,"metrics":["SBTDE"],"first_row_in_archive_order":{"model":"NevaClip","paper_title":"Contrastive Language-Image Pretrained Models are Zero-Shot Human Scanpath Predictors","paper_url":"/paper/constrastive-language-image-pretrained-models","paper_date":"2023-05-21","arxiv_id":"2305.12380","code_links":[],"syntology":null}},{"leaderboard":"/sota/scanpath-prediction-on-coutrot-dataset-1","slug":"scanpath-prediction-on-coutrot-dataset-1","dataset":"Coutrot Dataset 1","dataset_url":null,"rows_in_archive":1,"metrics":["Scaled time-delay embeddings","String-edit distance"],"first_row_in_archive_order":{"model":"G-EYMOL","paper_title":"Gravitational Laws of Focus of Attention","paper_url":"/paper/gravitational-laws-of-focus-of-attention","paper_date":"2019-06-04","arxiv_id":null,"code_links":[{"title":"dariozanca/G-Eymol","url":"https://github.com/dariozanca/G-Eymol"}],"syntology":null}},{"leaderboard":"/sota/scanpath-prediction-on-fixatons","slug":"scanpath-prediction-on-fixatons","dataset":"FixaTons","dataset_url":"/dataset/fixatons","rows_in_archive":1,"metrics":["Scaled time-delay embeddings","String-edit distance"],"first_row_in_archive_order":{"model":"G-EYMOL","paper_title":"Gravitational Laws of Focus of Attention","paper_url":"/paper/gravitational-laws-of-focus-of-attention","paper_date":"2019-06-04","arxiv_id":null,"code_links":[{"title":"dariozanca/G-Eymol","url":"https://github.com/dariozanca/G-Eymol"}],"syntology":null}}],"datasets":[{"url":"/dataset/fixatons","name":"FixaTons","full_name":"","num_papers_in_archive":2},{"url":"/dataset/capmit1003","name":"CapMIT1003","full_name":"","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":13,"of":13,"tagged_in_all":34,"items":[{"url":"/paper/artificially-generated-visual-scanpath","title":"Artificially Generated Visual Scanpath Improves Multi-label Thoracic Disease Classification in Chest X-Ray Images","date":"2025-03-01","arxiv_id":"2503.00657","repositories_listed":1,"syntology":null},{"url":"/paper/few-shot-personalized-scanpath-prediction","title":"Few-shot Personalized Scanpath Prediction","date":"2025-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/oat-object-level-attention-transformer-for","title":"OAT: Object-Level Attention Transformer for Gaze Scanpath Prediction","date":"2024-07-18","arxiv_id":"2407.13335","repositories_listed":1,"syntology":{"n":18,"n_ran":15,"n_unverified":3,"n_pointer_only":18}},{"url":"/paper/pathformer3d-a-3d-scanpath-transformer-for","title":"Pathformer3D: A 3D Scanpath Transformer for 360° Images","date":"2024-07-15","arxiv_id":"2407.10563","repositories_listed":1,"syntology":null},{"url":"/paper/gazeformer-scalable-effective-and-fast","title":"Gazeformer: Scalable, Effective and Fast Prediction of Goal-Directed Human Attention","date":"2023-03-27","arxiv_id":"2303.15274","repositories_listed":1,"syntology":{"n":2,"n_ran":0,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/predicting-human-attention-using","title":"Unifying Top-down and Bottom-up Scanpath Prediction Using Transformers","date":"2023-03-16","arxiv_id":"2303.09383","repositories_listed":1,"syntology":null},{"url":"/paper/scandmm-a-deep-markov-model-of-scanpath","title":"ScanDMM: A Deep Markov Model of Scanpath Prediction for 360deg Images","date":"2023-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/predicting-human-scanpaths-in-visual-question","title":"Predicting Human Scanpaths in Visual Question Answering","date":"2021-06-19","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/on-gaze-deployment-to-audio-visual-cues-of","title":"On gaze deployment to audio-visual cues of social interactions","date":"2020-09-02","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/gravitational-laws-of-focus-of-attention","title":"Gravitational Laws of Focus of Attention","date":"2019-06-04","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/pathgan-visual-scanpath-prediction-with","title":"PathGAN: Visual Scanpath Prediction with Generative Adversarial Networks","date":"2018-09-03","arxiv_id":"1809.00567","repositories_listed":1,"syntology":null},{"url":"/paper/variational-laws-of-visual-attention-for","title":"Variational Laws of Visual Attention for Dynamic Scenes","date":"2017-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/saltinet-scan-path-prediction-on-360-degree","title":"SaltiNet: Scan-path Prediction on 360 Degree Images using Saliency Volumes","date":"2017-07-11","arxiv_id":"1707.03123","repositories_listed":1,"syntology":null}],"syntology_records":2,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}