{"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/recurrent-flow-guided-semantic-forecasting","title":"Recurrent Flow-Guided Semantic Forecasting","arxiv_id":"1809.08318","date":"2018-09-21","proceeding":null,"authors":["Adam M. Terwilliger","Garrick Brazil","Xiaoming Liu"],"abstract":"Understanding the world around us and making decisions about the future is a\ncritical component to human intelligence. As autonomous systems continue to\ndevelop, their ability to reason about the future will be the key to their\nsuccess. Semantic anticipation is a relatively under-explored area for which\nautonomous vehicles could take advantage of (e.g., forecasting pedestrian\ntrajectories). Motivated by the need for real-time prediction in autonomous\nsystems, we propose to decompose the challenging semantic forecasting task into\ntwo subtasks: current frame segmentation and future optical flow prediction.\nThrough this decomposition, we built an efficient, effective, low overhead\nmodel with three main components: flow prediction network, feature-flow\naggregation LSTM, and end-to-end learnable warp layer. Our proposed method\nachieves state-of-the-art accuracy on short-term and moving objects semantic\nforecasting while simultaneously reducing model parameters by up to 95% and\nincreasing efficiency by greater than 40x.","url_abs":"http://arxiv.org/abs/1809.08318v2","url_pdf":"http://arxiv.org/pdf/1809.08318v2.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":"recurrent-flow-guided-semantic-forecasting","repo_url":"https://github.com/adamtwig/segpred","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"autonomous-vehicles","task_name":"Autonomous Vehicles"},{"task_slug":"optical-flow-estimation","task_name":"Optical Flow Estimation"},{"task_slug":"prediction","task_name":"Prediction"}],"methods":[{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1809.08318","atlas_url":"https://app.syntology.ai/?focus=1809.08318","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}