Datasets
Datasets and benchmarks grouped by research topic for faster browsing.
Surveillance and Video Understanding
GroundMoRe
Video questions paired with spatiotemporal object masks for reasoning about motion and grounding answers at the pixel level.
Andong Deng, Tongjia Chen, Shoubin Yu, Taojiannan Yang, Lincoln Spencer, Yapeng Tian, Ajmal Saeed Mian, Mohit Bansal, Chen Chen
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2025
CoMET-Bench
Long-video benchmark with new conditional queries and temporal annotations for finding and counting all matching events, including queries with no matching event.
Video files require approved access through the Hugging Face dataset page.
Yuanhao Zou, Arthad Kulkarni, Lucas Toñanez, Lincoln Spencer, Guangyu Sun, Tianxingjian Ding, Andong Deng, Yi Li, Shuangjun Liu, Yuan Li, Dashan Gao, Ning Bi, Taotao Jing, Shuai Zhang, Chen Chen
Conference on Neural Information Processing Systems (NeurIPS), 2026
UCF-Crime
Large-scale real-world surveillance dataset with 1,900 long videos and 13 anomaly categories for anomaly detection and recognition.
The zip file has a corrupted "Anomaly_Train.txt"; the paper project page provides the corrected file.
Waqas Sultani, Chen Chen, Mubarak Shah
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018
MSAD
Multi-Scenario Anomaly Detection dataset covering 14 surveillance scenarios with diverse viewpoints, lighting, and weather conditions.
Liyun Zhu, Lei Wang, Arjun Raj, Tom Gedeon, Chen Chen
Thirty-eighth Annual Conference on Neural Information Processing Systems (NeurIPS), 2024
UCA (UCF-Crime Annotation)
Sentence-level surveillance video-language annotations built on top of UCF-Crime for multimodal event understanding and temporal grounding.
Built on top of UCF-Crime with fine-grained sentence and timing annotations.
Tongtong Yuan, Xuange Zhang, Kun Liu, Bo Liu , Chen Chen, Jian Jin, Zhenzhen Jiao
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2024
Geospatial and Localization
VIGORv2
An extension of VIGOR with newly collected aerial imagery, layout maps, and text descriptions for geometry-guided cross-view synthesis.
The authors provide an access-request form through the repository's dataset instructions.
Ahmad Arrabi, Xiaohan Zhang, Waqas Sultani, Chen Chen, Safwan Wshah
IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2025
Cross-View Geolocalization Dataset
Street-view and bird's-eye-view image-pair dataset collected around Pittsburgh, Orlando, and Manhattan for cross-view geo-localization.
Yicong Tian, Chen Chen, Mubarak Shah
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017
VIGOR
Large-scale benchmark for realistic cross-view image geo-localization beyond one-to-one street-to-aerial retrieval.
Sijie Zhu, Taojiannan Yang, Chen Chen
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021
GAMa
Cross-view geo-localization resource that matches ground videos against aerial imagery instead of single street-view frames.
Shruti Vyas, Chen Chen, Mubarak Shah
European Conference on Computer Vision (ECCV), 2022
Human Motion, Hand Pose, and Sign
UTD-MHAD
Depth-plus-inertial human action dataset with 27 actions for multimodal action recognition and sensor-fusion research.
Chen Chen, Roozbeh Jafari, Nasser Kehtarnavaz
IEEE International Conference on Image Processing (ICIP), 2015
RenderIH
Large-scale synthetic resource with one million photorealistic images for 3D interacting hand pose estimation.
Lijun Li, Linrui Tian, Xindi Zhang, Qi Wang, Bang Zhang, Liefeng Bo, Mengyuan Liu, Chen Chen
IEEE/CVF International Conference on Computer Vision (ICCV), 2023
Prompt2Sign
Multilingual sign-language production resource introduced for prompt-to-sign generation and Sign LLM training.
Sen Fang, Lei Wang, Ce Zheng, Yapeng Tian, Chen Chen
IEEE/CVF International Conference on Computer Vision (ICCV) Workshop (CV4A11y Workshop), 2025
BEAR
Benchmark suite spanning 18 video datasets for fair evaluation across anomaly, gesture, daily, sports, and instructional action settings.
Andong Deng, Taojiannan Yang, Chen Chen
IEEE/CVF International Conference on Computer Vision (ICCV), 2023
Medical and Biomedical
UCF-MultiOrgan-Path
Public histopathology dataset for organ classification with research-ready whole-slide image patches and curated labels.
Md Sanzid Bin Hossain, Yelena Piazza, Jacob Braun, Anthony Bilic, Michael Hsieh, Samir Fouissi, Alexander Borowsky, Hatem Kaseb, Amoy Fraser, Britney-Ann Wray, Chen Chen, Liqiang Wang, Mujtaba Husain, Dexter Hadley
medRxiv 2024.11.05.24316736
Malaria Life-Cycle Dataset
Microscopy dataset and benchmark for malaria life-cycle classification and parasite detection in thin blood smear images.
Qazi Ammar Arshad, Mohsen Ali, Saeed-ul Hassan, Chen Chen, Ayisha Imran, Ghulam Rasul, Waqas Sultani
Neural Computing and Applications, 2021
Multimodal Reasoning and Evaluation
FoodSense
Human-annotated multisensory food resource with ratings and grounded explanations for taste, smell, texture, and sound.
Sabab Ishraq, Aarushi Aarushi, Juncai Jiang, Chen Chen
IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshop, 2026
SciVideoBench
Scientific video benchmark for advanced spatiotemporal reasoning across more than 25 scientific subjects.
Andong Deng, Taojiannan Yang, Shoubin Yu, Lincoln Spencer, Mohit Bansal, Chen Chen, Serena Yeung-Levy, Xiaohan Wang
Forty-third International Conference on Machine Learning (ICML), 2026
VEBench
Video editing benchmark for technique recognition and operational reasoning over realistic multi-video editing workflows.
Andong Deng, Dawei Du, Zhenfang Chen, Wen Zhong, Fan Chen, Guang Chen, Chia-Wen Kuo, Longyin Wen, Chen Chen, Sijie Zhu
IEEE Conference on Computer Vision and Pattern Recognition (CVPR) - Findings Track, 2026
VERIFY
Visual reasoning benchmark with human-annotated reasoning paths for auditing explanation quality and multimodal reasoning fidelity.
Jing Bi, Junjia Guo, Guangyu Sun, Susan Liang, Luchuan Song, Yolo Y. Tang, Jinxi He, Jiarui Wu, Ali Vosoughi, Chen Chen, Jason J Corso, Chenliang Xu
Conference on Language Modeling (COLM), 2026
Important Notice
Please cite the associated paper and consult each resource's project or dataset page for its license, access requirements, and permitted uses. Terms differ by resource; a public link does not imply unrestricted use.