@inproceedings{longvalevisionaudiolanguageevent,
  title = {LongVALE: Vision-Audio-Language-Event Benchmark Towards Time-Aware Omni-Modal Perception of Long Videos},
  author = {Tiantian Geng and Jinrui Zhang and Qingni Wang and Teng Wang and Jinming Duan and Feng Zheng},
  year = {2024},
  booktitle = {CVPR 2025 1},
  eprint = {2411.19772},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2411.19772v3},
}