{"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-ladder-networks","title":"Video Ladder Networks","arxiv_id":"1612.01756","date":"2016-12-06","proceeding":null,"authors":["Francesco Cricri","Xingyang Ni","Mikko Honkala","Emre Aksu","Moncef Gabbouj"],"abstract":"We present the Video Ladder Network (VLN) for efficiently generating future\nvideo frames. VLN is a neural encoder-decoder model augmented at all layers by\nboth recurrent and feedforward lateral connections. At each layer, these\nconnections form a lateral recurrent residual block, where the feedforward\nconnection represents a skip connection and the recurrent connection represents\nthe residual. Thanks to the recurrent connections, the decoder can exploit\ntemporal summaries generated from all layers of the encoder. This way, the top\nlayer is relieved from the pressure of modeling lower-level spatial and\ntemporal details. Furthermore, we extend the basic version of VLN to\nincorporate ResNet-style residual blocks in the encoder and decoder, which help\nimproving the prediction results. VLN is trained in self-supervised regime on\nthe Moving MNIST dataset, achieving competitive results while having very\nsimple structure and providing fast inference.","url_abs":"http://arxiv.org/abs/1612.01756v3","url_pdf":"http://arxiv.org/pdf/1612.01756v3.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-ladder-networks","repo_url":"https://github.com/rohilrao/DeepLearning_with_PyTorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}