{"url":"/sota/trajectory-prediction-on-trajnet","task":{"name":"Trajectory Prediction","url":"/task/trajectory-prediction","note":null},"dataset":{"name":"TrajNet++","url":"/dataset/trajnet-1"},"category":"Computer Vision","categories":["Computer Vision","Time Series"],"category_note":null,"description":"**Trajectory Prediction** is the problem of predicting the short-term (1-3 seconds) and long-term (3-5 seconds) spatial coordinates of various road-agents such as cars, buses, pedestrians, rickshaws, and animals, etc. These road-agents have different dynamic behaviors that may correspond to aggressive or conservative driving styles.\r\n\r\n\r\n<span class=\"description-source\">Source: [Forecasting Trajectory and Behavior of Road-Agents Using Spectral Clustering in Graph-LSTMs ](https://arxiv.org/abs/1912.01118)</span>","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["FDE","COL"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"FDE":null,"COL":null}},"counts":{"rows":3,"rows_with_code":3,"rows_with_paper_page":3,"rows_dated":3,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"Social-NCE + Social-LSTM","metrics":{"COL":"5.31","FDE":"1.14"},"uses_additional_data":false,"paper_date":"2020-12-21","paper":"/paper/social-nce-contrastive-learning-of-socially","paper_url":"https://arxiv.org/abs/2012.11717v3","paper_title":"Social NCE: Contrastive Learning of Socially-aware Motion Representations","code":"https://github.com/vita-epfl/social-nce","n_code_links":4,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":3}},{"rank_in_archive_order":2,"model":"U-LSTM + Social Pooling","metrics":{"COL":"6.560","FDE":"1.150"},"uses_additional_data":false,"paper_date":"2021-06-01","paper":"/paper/asymmetrical-bi-rnn-for-pedestrian-trajectory","paper_url":"https://arxiv.org/abs/2106.04419v2","paper_title":"Asymmetrical Bi-RNN for pedestrian trajectory encoding","code":"https://github.com/JosephGesnouin/Asymmetrical-Bi-RNNs-to-encode-pedestrian-trajectories","n_code_links":1,"syntology":null},{"rank_in_archive_order":3,"model":"Social LSTM","metrics":{"COL":"7.59","FDE":"1.17"},"uses_additional_data":false,"paper_date":"2020-07-07","paper":"/paper/human-trajectory-forecasting-in-crowds-a-deep","paper_url":"https://arxiv.org/abs/2007.03639v3","paper_title":"Human Trajectory Forecasting in Crowds: A Deep Learning Perspective","code":"https://github.com/vita-epfl/trajnetplusplusbaselines","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":10,"n_samples":10,"n_pointer_only_licence":0}}],"since_archive":{"present":false,"note":"No Syntology-extracted rows are published in this build."},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":2,"rows_with_any_sample_ran":1,"distinct_papers_with_graph_line":2,"distinct_papers_with_any_sample_ran":1,"samples_over_distinct_papers":{"n_ran":3,"n_unverified":10,"n_samples":13,"n_pointer_only_licence":3,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":3,"n_unverified":10,"n_samples":13,"n_pointer_only_licence":3,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}