{"url":"/dataset/trajnet-1","name":"TrajNet","full_name":null,"description_markdown":"The **TrajNet** Challenge represents a large multi-scenario forecasting benchmark. The challenge consists on  predicting 3161 human trajectories, observing for each trajectory 8 consecutive ground-truth values (3.2 seconds) i.e., t−7,t−6,…,t, in world plane coordinates (the so-called world plane Human-Human protocol) and forecasting the following 12 (4.8 seconds), i.e., t+1,…,t+12. The 8-12-value protocol is consistent with the most trajectory forecasting approaches, usually focused on the 5-dataset ETH-univ + ETH-hotel + UCY-zara01 + UCY-zara02 + UCY-univ. Trajnet extends substantially the 5-dataset scenario by diversifying the training data, thus stressing the flexibility and generalization one approach has to exhibit when it comes to unseen scenery/situations. In fact, TrajNet is a superset of diverse datasets that requires to train on four families of trajectories, namely 1) BIWI Hotel (orthogonal bird’s eye flight view, moving people), 2) Crowds UCY (3 datasets, tilted bird’s eye view, camera mounted on building or utility poles, moving people), 3) MOT PETS (multisensor, different human activities) and 4) Stanford Drone Dataset (8 scenes, high orthogonal bird’s eye flight view, different agents as people, cars etc. ), for a total of 11448 trajectories. Testing is requested on diverse partitions of BIWI Hotel, Crowds UCY, Stanford Drone Dataset, and is evaluated by a specific server (ground-truth testing data is unavailable for applicants).\r\n\r\nSource: [Transformer Networks for Trajectory Forecasting](https://arxiv.org/abs/2003.08111)\r\nImage Source: [http://trajnet.stanford.edu/](http://trajnet.stanford.edu/)","description_withheld":null,"homepage":"http://trajnet.stanford.edu/","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/an-evaluation-of-trajectory-prediction","title":"An Evaluation of Trajectory Prediction Approaches and Notes on the TrajNet Benchmark","first_author":"Stefan Becker","url":null},"license":{"name":"Unknown","url":null},"modalities":[{"name":"Images","url":"/datasets/modality/images"}],"tasks":[{"name":"Trajectory Prediction","url":"/task/trajectory-prediction","datasets_with_task":"/datasets/task/trajectory-prediction"},{"name":"Trajectory Forecasting","url":"/task/trajectory-forecasting","datasets_with_task":"/datasets/task/trajectory-forecasting"},{"name":"Decision Making","url":"/task/decision-making","datasets_with_task":"/datasets/task/decision-making"}],"languages":[],"variants":["TrajNet++","TrajNet"],"data_loaders":[],"num_papers_in_archive":12,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/trajectory-forecasting-on-trajnet","task":"Trajectory Forecasting","dataset_variant":"TrajNet++","rows":3,"metrics":["FDE","COL"],"first_row_in_archive_order":{"model":"Social NCE + Social LSTM","paper":"/paper/social-nce-contrastive-learning-of-socially","metrics":{"COL":"5.31","FDE":"1.14"},"code_links":[{"title":"vita-epfl/social-nce","url":"https://github.com/vita-epfl/social-nce"},{"title":"vita-epfl/social-nce-crowdnav","url":"https://github.com/vita-epfl/social-nce-crowdnav"},{"title":"YuejiangLIU/social-nce-trajectron-plus-plus","url":"https://github.com/YuejiangLIU/social-nce-trajectron-plus-plus"},{"title":"qiyan98/social-nce-stgcnn","url":"https://github.com/qiyan98/social-nce-stgcnn"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/trajectory-prediction-on-trajnet","task":"Trajectory Prediction","dataset_variant":"TrajNet++","rows":3,"metrics":["FDE","COL"],"first_row_in_archive_order":{"model":"Social-NCE + Social-LSTM","paper":"/paper/social-nce-contrastive-learning-of-socially","metrics":{"COL":"5.31","FDE":"1.14"},"code_links":[{"title":"vita-epfl/social-nce","url":"https://github.com/vita-epfl/social-nce"},{"title":"vita-epfl/social-nce-crowdnav","url":"https://github.com/vita-epfl/social-nce-crowdnav"},{"title":"YuejiangLIU/social-nce-trajectron-plus-plus","url":"https://github.com/YuejiangLIU/social-nce-trajectron-plus-plus"},{"title":"qiyan98/social-nce-stgcnn","url":"https://github.com/qiyan98/social-nce-stgcnn"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/asymmetrical-bi-rnn-for-pedestrian-trajectory","title":"Asymmetrical Bi-RNN for pedestrian trajectory encoding","date":"2021-06-01","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/social-nce-contrastive-learning-of-socially","title":"Social NCE: Contrastive Learning of Socially-aware Motion Representations","date":"2020-12-21","rows_on_this_dataset":2,"code_links":4,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":3,"samples_unverified":0,"pointer_only_for_licence":3,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/human-trajectory-forecasting-in-crowds-a-deep","title":"Human Trajectory Forecasting in Crowds: A Deep Learning Perspective","date":"2020-07-07","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":10,"samples_ran":0,"samples_unverified":10,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":2,"samples_harvested":13,"samples_ran":3,"samples_unverified":10,"pointer_only_for_licence":3,"papers_with_no_sample_that_ran":1,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}