{"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/location-dependency-in-video-prediction","title":"Location Dependency in Video Prediction","arxiv_id":"1810.04937","date":"2018-10-11","proceeding":null,"authors":["Niloofar Azizi","Hafez Farazi","Sven Behnke"],"abstract":"Deep convolutional neural networks are used to address many computer vision\nproblems, including video prediction. The task of video prediction requires\nanalyzing the video frames, temporally and spatially, and constructing a model\nof how the environment evolves. Convolutional neural networks are spatially\ninvariant, though, which prevents them from modeling location-dependent\npatterns. In this work, the authors propose location-biased convolutional\nlayers to overcome this limitation. The effectiveness of location bias is\nevaluated on two architectures: Video Ladder Network (VLN) and Convolutional\nredictive Gating Pyramid (Conv-PGP). The results indicate that encoding\nlocation-dependent features is crucial for the task of video prediction. Our\nproposed methods significantly outperform spatially invariant models.","url_abs":"http://arxiv.org/abs/1810.04937v2","url_pdf":"http://arxiv.org/pdf/1810.04937v2.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":"location-dependency-in-video-prediction","repo_url":"https://github.com/AIS-Bonn/LocDepVideoPrediction","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"prediction","task_name":"Prediction"},{"task_slug":"video-prediction","task_name":"Video Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}