DataCube: A Video Retrieval Platform via Natural Language Semantic Profiling
Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence. Demo Track. Pages 8415-8418.
https://doi.org/10.24963/ijcai.2026/969
Keywords
- AI: Search
- AI: Computer Vision
- AI: Natural Language Processing
- AI: Data Mining
Abstract
Large-scale video repositories are increasingly available for modern video understanding and generation tasks. However, transforming raw videos into high-quality, task-specific datasets remains costly and inefficient. We present DataCube, an intelligent platform for automatic video processing, multi-dimensional profiling, and query-driven retrieval. DataCube constructs structured semantic representations of video clips and supports hybrid retrieval with neural re-ranking and deep semantic matching. Through an interactive web interface, users can efficiently construct customized video subsets from massive repositories for training, analysis, and evaluation, and build searchable systems over their own private video collections. The system is publicly accessible at https://datacube.baai.ac.cn/. Demo Video: https://youtu.be/L7bKfPBm2tU
@inproceedings{ijcai2026p969,
title = {DataCube: A Video Retrieval Platform via Natural Language Semantic Profiling},
author = {Ju, Yiming and Zhao, Hanyu and Ma, Quanyue and Hao, Donglin and Wu, Chenwei and Li, Ming and Wang, Songjing and Pan, Tengfei},
booktitle = {Proceedings of the Thirty-Fifth International Joint Conference on
Artificial Intelligence, {IJCAI-26}},
publisher = {International Joint Conferences on Artificial Intelligence Organization},
editor = {Diego Calvanese},
pages = {8415--8418},
year = {2026},
month = {8},
note = {Demo Track},
doi = {10.24963/ijcai.2026/969},
url = {https://doi.org/10.24963/ijcai.2026/969},
}
TY - CPAPER TI - DataCube: A Video Retrieval Platform via Natural Language Semantic Profiling AU - Ju, Yiming AU - Zhao, Hanyu AU - Ma, Quanyue AU - Hao, Donglin AU - Wu, Chenwei AU - Li, Ming AU - Wang, Songjing AU - Pan, Tengfei T2 - Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-26 PB - International Joint Conferences on Artificial Intelligence Organization PY - 2026 SP - 8415 EP - 8418 DO - 10.24963/ijcai.2026/969 UR - https://doi.org/10.24963/ijcai.2026/969 ER -Copied
Machine-readable versions of this paper, for tools and AI agents: