{"id":23478161,"url":"https://github.com/mtli/sap","last_synced_at":"2025-04-14T21:31:31.917Z","repository":{"id":141260941,"uuid":"289312814","full_name":"mtli/sAP","owner":"mtli","description":"Code for Towards Streaming Perception (ECCV 2020) :car:","archived":false,"fork":false,"pushed_at":"2021-04-14T04:05:29.000Z","size":10971,"stargazers_count":94,"open_issues_count":0,"forks_count":19,"subscribers_count":8,"default_branch":"master","last_synced_at":"2024-01-29T16:33:43.223Z","etag":null,"topics":["detection","forecasting","instance-segmentation","streaming-perception","tracking"],"latest_commit_sha":null,"homepage":"http://www.cs.cmu.edu/~mengtial/proj/streaming/","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/mtli.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null}},"created_at":"2020-08-21T16:14:27.000Z","updated_at":"2024-01-04T16:49:37.000Z","dependencies_parsed_at":"2023-09-22T07:01:56.582Z","dependency_job_id":"86e82aa5-4952-4e3b-9770-2a5a32968da2","html_url":"https://github.com/mtli/sAP","commit_stats":{"total_commits":29,"total_committers":1,"mean_commits":29.0,"dds":0.0,"last_synced_commit":"0a459390b6d8f6fbf16a876fa52b6f096395193f"},"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mtli%2FsAP","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mtli%2FsAP/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mtli%2FsAP/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mtli%2FsAP/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/mtli","download_url":"https://codeload.github.com/mtli/sAP/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":231142956,"owners_count":18334321,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["detection","forecasting","instance-segmentation","streaming-perception","tracking"],"created_at":"2024-12-24T19:16:37.910Z","updated_at":"2024-12-24T19:16:44.723Z","avatar_url":"https://github.com/mtli.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# sAP \u0026mdash; Code for Towards Streaming Perception\r\n\r\n\u003cp align=\"center\"\u003e\u003cimg alt=\"Teaser\" src=\"doc/img/streaming.jpg\" width=\"500px\"\u003e\u003c/p\u003e\r\n\r\n![#fc4903](https://via.placeholder.com/15/fc4903/000000?text=+) ECCV Best Paper Honorable Mention Award\r\n\r\n![#fcc203](https://via.placeholder.com/15/fcc203/000000?text=+) Feb 2021: Announcing the [Streaming Perception Challenge](https://eval.ai/web/challenges/challenge-page/800/overview) (CVPR 2021)!\r\n\r\nThis repo contains code for our ECCV 2020 [**paper**](https://arxiv.org/abs/2005.10420) (Towards Streaming Perception). sAP stands for streaming Average Precision.\r\n\r\nThe dataset used in this project (Argoverse-HD) can be found on the [**project page**](http://www.cs.cmu.edu/~mengtial/proj/streaming/).\r\n\r\nApr 2021: Note that the code has been updated to match the setting in the streaming perception challenge (mostly about working with newer dependencies). To reproduce the numbers in our paper, please check out the [ECCV paper branch](../../tree/ECCV-paper).\r\n\r\n## Contents\r\n\r\n- Offline detection\r\n- Streaming (real-time online) detection\r\n- Streaming tracking \\\u0026 forecasting\r\n- Simulated streaming detection, tracking, \\\u0026 forecasting\r\n- Simulated streaming detection, tracking, \\\u0026 forecasting with infinite GPUs \r\n- Meta-detector Streamer\r\n- Streaming evaluation\r\n- Single-frame schedule simulator\r\n- Helper functions for visualization\r\n\r\n\r\n\u003cp align=\"center\"\u003e\u003cimg alt=\"Teaser\" src=\"doc/img/latency-aware.gif\" width=\"600px\" style=\" border: 1px solid black;\r\n  -webkit-box-shadow: 2px 2px 1px #666;\r\n  box-shadow: 2px 2px 1px #666;\"\u003e\u003c/p\u003e\r\n\r\n## Getting started\r\n\r\n1. Follow the instructions [here](doc/data_setup.md) to download and set up the dataset.\r\n1. Follow the instructions [here](doc/code_setup.md) to install the dependencies.\r\n1. Check out the examples to run various tasks in `exp/*`. The documentation for these tasks can be found [here](doc/tasks.md).\r\n\r\n\r\n## Citation\r\nIf you use the code or the data for your research, please cite the paper:\r\n\r\n```\r\n@article{Li2020StreamingP,\r\n  title={Towards Streaming Perception},\r\n  author={Li, Mengtian and Wang, Yuxiong and Ramanan, Deva},\r\n  journal={ECCV},\r\n  year={2020}\r\n}\r\n```\r\n\r\n## Acknowledgement\r\nWe would like to thank the [mmdetection](https://github.com/open-mmlab/mmdetection) team for implementing so many different detectors in a single awesome repo with a unified interface! This greatly reduced our efforts to evaluate different detectors under our streaming setting.\r\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmtli%2Fsap","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmtli%2Fsap","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmtli%2Fsap/lists"}