sutd-trafficqa
[CVPR2021] SUTD-TrafficQA: A Question Answering Benchmark and an Efficient Network for Video Reasoning over Traffic Events
Science Score: 41.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
✓CITATION.cff file
Found CITATION.cff file -
✓codemeta.json file
Found codemeta.json file -
○.zenodo.json file
-
○DOI references
-
✓Academic publication links
Links to: arxiv.org, researchgate.net -
○Academic email domains
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (5.8%) to scientific vocabulary
Keywords
Repository
[CVPR2021] SUTD-TrafficQA: A Question Answering Benchmark and an Efficient Network for Video Reasoning over Traffic Events
Basic Info
- Host: GitHub
- Owner: sutdcv
- Language: JavaScript
- Default Branch: master
- Homepage: https://sutdcv.github.io/SUTD-TrafficQA/
- Size: 6 MB
Statistics
- Stars: 53
- Watchers: 4
- Forks: 2
- Open Issues: 2
- Releases: 0
Topics
Metadata Files
README.md
SUTD-TrafficQA
A challenging Video Question Answering (VQA) Benchmark based on real-world traffic scenes.
Updates:
-
Jul 2021The dataset is publicly released. You may request download now. -
Jun 2021The dataset usage details are available now. -
May 2021The dataset homepage is live now. -
Feb 2021~~The dataset is available upon email request.~~
Paper
Our 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], [arXiv:2103.15538], and [ResearchGate].
Dataset
- Annotation Example examples/annotation_sample.jsonl
- Jsonl Reader Example examples/jsonl_reader.py
- Appearance Feature Preprocessing examples/preprocessvideoappearance_example.py
- Motion Feature Preprocessing examples/preprocessvideomotion_example.py
- Dataloader examples/dataloader_example.py
- Download Dataset
Citation
bibtex
@InProceedings{Xu_2021_CVPR,
author = {Xu, Li and Huang, He and Liu, Jun},
title = {{SUTD-TrafficQA: A Question Answering Benchmark and an Efficient Network for Video Reasoning Over Traffic Events}},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2021},
pages = {9878-9888}
}
Acknowledgment
Contributors: Lin Yutian, Tran Nguyen Bao Long, Liu Renhang, Qiao Yingjie, Xun Long Ng, Koh Kai Ting, Christabel Dorothy
Code Reference: thaolmk54 / hcrn-videoqa
Contact
-
li_xu [AT] mymail.sutd.edu.sg -
he_huang [AT] mymail.sutd.edu.sg
Owner
- Name: SUTD Computer Vision & Learning Group (VLG)
- Login: sutdcv
- Kind: organization
- Location: Singapore
- Website: https://people.sutd.edu.sg/~jun_liu/
- Repositories: 5
- Profile: https://github.com/sutdcv
Computer Vision and Learning Research at Singapore University of Technology and Design
Citation (CITATION)
@InProceedings{Xu_2021_CVPR,
author = {Xu, Li and Huang, He and Liu, Jun},
title = {SUTD-TrafficQA: A Question Answering Benchmark and an Efficient Network for Video Reasoning Over Traffic Events},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2021},
pages = {9878-9888}
}
GitHub Events
Total
- Watch event: 6
Last Year
- Watch event: 6
Dependencies
- actions/checkout v2 composite
- 1260 dependencies
- @material-ui/core ^4.11.4
- @testing-library/jest-dom ^5.12.0
- @testing-library/react ^11.2.7
- @testing-library/user-event ^12.8.3
- axios ^0.21.1
- country-list ^2.2.0
- react ^17.0.2
- react-bootstrap ^1.6.0
- react-code-blocks ^0.0.8
- react-dom ^17.0.2
- react-router-dom ^5.2.0
- react-scripts ^5.0.1
- web-vitals ^1.1.2