@article{deteclapenhancingaudiovisual,
  title = {DETECLAP: Enhancing Audio-Visual Representation Learning with Object Information},
  author = {Shota Nakada and Taichi Nishimura and Hokuto Munakata and Masayoshi Kondo and Tatsuya Komatsu},
  year = {2024},
  eprint = {2409.11729},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2409.11729v1},
}