{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/deja-vu-motion-prediction-in-static-images","title":"Deja Vu: Motion Prediction in Static Images","arxiv_id":"1803.06951","date":"2018-03-19","proceeding":null,"authors":["Silvia L. Pintea","Jan C. van Gemert","Arnold W. M. Smeulders"],"abstract":"This paper proposes motion prediction in single still images by learning it\nfrom a set of videos. The building assumption is that similar motion is\ncharacterized by similar appearance. The proposed method learns local motion\npatterns given a specific appearance and adds the predicted motion in a number\nof applications. This work (i) introduces a novel method to predict motion from\nappearance in a single static image, (ii) to that end, extends of the\nStructured Random Forest with regression derived from first principles, and\n(iii) shows the value of adding motion predictions in different tasks such as:\nweak frame-proposals containing unexpected events, action recognition, motion\nsaliency. Illustrative results indicate that motion prediction is not only\nfeasible, but also provides valuable information for a number of applications.","url_abs":"http://arxiv.org/abs/1803.06951v2","url_pdf":"http://arxiv.org/pdf/1803.06951v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"deja-vu-motion-prediction-in-static-images","repo_url":"https://github.com/SilviaLauraPintea/DejaVu","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"action-recognition-in-videos","task_name":"Action Recognition"},{"task_slug":"prediction","task_name":"Prediction"},{"task_slug":"action-recognition","task_name":"Temporal Action Localization"},{"task_slug":"motion-prediction","task_name":"motion prediction"},{"task_slug":"regression-1","task_name":"regression"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}