{"id":13435333,"url":"https://github.com/sutdcv/SUTD-TrafficQA","last_synced_at":"2025-03-18T02:31:52.776Z","repository":{"id":44393173,"uuid":"352053951","full_name":"sutdcv/SUTD-TrafficQA","owner":"sutdcv","description":"[CVPR2021] SUTD-TrafficQA: A Question Answering Benchmark and an Efficient Network for Video Reasoning over Traffic Events","archived":false,"fork":false,"pushed_at":"2024-08-19T04:17:43.000Z","size":6289,"stargazers_count":49,"open_issues_count":2,"forks_count":2,"subscribers_count":4,"default_branch":"master","last_synced_at":"2024-08-19T05:29:40.897Z","etag":null,"topics":["annotations","cvpr","cvpr2021","dataset","multimodal","multimodal-deep-learning","paper","traffic-events","video-qa","video-reasoning","vqa","vqa-dataset"],"latest_commit_sha":null,"homepage":"https://sutdcv.github.io/SUTD-TrafficQA/","language":"JavaScript","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/sutdcv.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":"CITATION","codeowners":null,"security":null,"support":null}},"created_at":"2021-03-27T11:20:40.000Z","updated_at":"2024-08-19T04:16:54.000Z","dependencies_parsed_at":"2023-01-28T08:46:12.282Z","dependency_job_id":null,"html_url":"https://github.com/sutdcv/SUTD-TrafficQA","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sutdcv%2FSUTD-TrafficQA","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sutdcv%2FSUTD-TrafficQA/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sutdcv%2FSUTD-TrafficQA/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sutdcv%2FSUTD-TrafficQA/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/sutdcv","download_url":"https://codeload.github.com/sutdcv/SUTD-TrafficQA/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":221704719,"owners_count":16866818,"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":["annotations","cvpr","cvpr2021","dataset","multimodal","multimodal-deep-learning","paper","traffic-events","video-qa","video-reasoning","vqa","vqa-dataset"],"created_at":"2024-07-31T03:00:34.922Z","updated_at":"2024-10-27T16:32:30.376Z","avatar_url":"https://github.com/sutdcv.png","language":"JavaScript","funding_links":[],"categories":["Awesome Papers","📋 Summary of Language-Enhanced Datasets","PFMs for Video Data"],"sub_categories":["Datasets"],"readme":"# [SUTD-TrafficQA](https://sutdcv.github.io/SUTD-TrafficQA/)\n\nA challenging **Video Question Answering (VQA)** Benchmark based on **real-world** traffic scenes.\n\n**Updates:**\n\n-   `Jul 2021` The dataset is publicly released. You may [request download](https://sutdcv.github.io/SUTD-TrafficQA/#/download) now.\n-   `Jun 2021` The [dataset usage details](https://sutdcv.github.io/SUTD-TrafficQA/#/explore) are available now.\n-   `May 2021` The dataset [homepage](https://sutdcv.github.io/SUTD-TrafficQA) is live now.\n-   `Feb 2021` ~~The dataset is available upon email request.~~\n\n## Paper\n\nOur paper at **CVPR 2021**, _SUTD-TrafficQA: A Question Answering Benchmark and an Efficient Network for Video Reasoning over Traffic Events_, is available at: [[CVF Open Access]](https://openaccess.thecvf.com/content/CVPR2021/html/Xu_SUTD-TrafficQA_A_Question_Answering_Benchmark_and_an_Efficient_Network_for_CVPR_2021_paper.html), [[arXiv:2103.15538]](https://arxiv.org/abs/2103.15538), and [[ResearchGate]](https://www.researchgate.net/publication/350432154_TrafficQA_A_Question_Answering_Benchmark_and_an_Efficient_Network_for_Video_Reasoning_over_Traffic_Events).\n\n## Dataset\n\n-   Annotation Example [examples/annotation_sample.jsonl](examples/annotation_sample.jsonl)\n-   Jsonl Reader Example [examples/jsonl_reader.py](examples/jsonl_reader.py)\n-   Appearance Feature Preprocessing [examples/preprocess_video_appearance_example.py](examples/preprocess_video_appearance_example.py)\n-   Motion Feature Preprocessing [examples/preprocess_video_motion_example.py](examples/preprocess_video_motion_example.py)\n-   Dataloader [examples/dataloader_example.py](examples/dataloader_example.py)\n-   [Download Dataset](https://sutdcv.github.io/SUTD-TrafficQA)\n\n## Citation\n\n```bibtex\n@InProceedings{Xu_2021_CVPR,\n    author    = {Xu, Li and Huang, He and Liu, Jun},\n    title     = {{SUTD-TrafficQA: A Question Answering Benchmark and an Efficient Network for Video Reasoning Over Traffic Events}},\n    booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},\n    month     = {June},\n    year      = {2021},\n    pages     = {9878-9888}\n}\n```\n\n## Acknowledgment\n\nContributors: [**Lin Yutian**](https://github.com/Lynn-020809), [**Tran Nguyen Bao Long**](https://github.com/TNBL265), [**Liu Renhang**](https://github.com/Samillynn), [**Qiao Yingjie**](https://github.com/YingjieQiao), **Xun Long Ng**, **Koh Kai Ting**, **Christabel Dorothy**\n\nCode Reference: [thaolmk54 / hcrn-videoqa](https://github.com/thaolmk54/hcrn-videoqa)\n\n## Contact\n\n-   `li_xu [AT] mymail.sutd.edu.sg`\n-   `he_huang [AT] mymail.sutd.edu.sg`\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsutdcv%2FSUTD-TrafficQA","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsutdcv%2FSUTD-TrafficQA","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsutdcv%2FSUTD-TrafficQA/lists"}