VERIFIED: A Video Corpus Moment Retrieval Benchmark for Fine-Grained Video Understanding

Official repository of NeurIPS D&B Track 2024 paper "VERIFIED: A Video Corpus Moment Retrieval Benchmark for Fine-Grained Video Understanding"

http://arxiv.org/abs/2410.08593

The datasets and codes are coming soon.

[2024.10.22] 🚀 We update our webpage for our work VERIFIED! See https://verified-neurips.github.io

[2024.11.26] 🚀 We release our fine-grained dataset with its document.

[2024.12.22] 🚀 We release our features of our *-FIG datasets.

[2025.1.20] 🚀 Since some users outside of China can not visit Baidu cloud, we release the features in Tsinghua Cloud.

Link: https://pan.baidu.com/s/1gww8nzbYAIONrMfS7GG1HA?pwd=nz7w

Code: nz7w

Tsinghua Cloud Link: https://cloud.tsinghua.edu.cn/d/e87d339b5b094905b615/

Thanks to the previous works. The videos are from:

Charades: https://prior.allenai.org/projects/charades

DiDeMo: https://github.com/LisaAnne/LocalizingMoments

ActivityNet: http://activity-net.org/

Citation

If you are interested in this work, cite

@misc{chen2024verifiedvideocorpusmoment,
      title={VERIFIED: A Video Corpus Moment Retrieval Benchmark for Fine-Grained Video Understanding}, 
      author={Houlun Chen and Xin Wang and Hong Chen and Zeyang Zhang and Wei Feng and Bin Huang and Jia Jia and Wenwu Zhu},
      year={2024},
      eprint={2410.08593},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2410.08593}, 
}