{"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/video-pixel-networks","title":"Video Pixel Networks","arxiv_id":"1610.00527","date":"2016-10-03","proceeding":"ICML 2017 8","authors":["Nal Kalchbrenner","Aaron van den Oord","Karen Simonyan","Ivo Danihelka","Oriol Vinyals","Alex Graves","Koray Kavukcuoglu"],"abstract":"We propose a probabilistic video model, the Video Pixel Network (VPN), that\nestimates the discrete joint distribution of the raw pixel values in a video.\nThe model and the neural architecture reflect the time, space and color\nstructure of video tensors and encode it as a four-dimensional dependency\nchain. The VPN approaches the best possible performance on the Moving MNIST\nbenchmark, a leap over the previous state of the art, and the generated videos\nshow only minor deviations from the ground truth. The VPN also produces\ndetailed samples on the action-conditional Robotic Pushing benchmark and\ngeneralizes to the motion of novel objects.","url_abs":"http://arxiv.org/abs/1610.00527v1","url_pdf":"http://arxiv.org/pdf/1610.00527v1.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":"video-pixel-networks","repo_url":"https://github.com/3ammor/Video-Pixel-Networks","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"video-prediction","task_name":"Video Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/video-prediction-on-kth","task":"Video Prediction","dataset":"KTH","model":"VPN","rank_in_archive_order":29,"of":31,"metrics":{"Cond":"10","PSNR":"23.76","Pred":"20","SSIM":"0.746"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1610.00527","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}