Model Card for Search-TTA-Sound

Fine-tuned on laion/clap-htsat-fused.

Citation

@article{tan2025searchtta,
      author  = {Derek Ming Siang Tan, Shailesh, Boyang Liu, Alok Raj, Qi Xuan Ang, Weiheng Dai, Tanishq Duhan, Jimmy Chiun, Yuhong Cao, Florian Shkurti, Guillaume Sartoretti},
      title   = {Search-TTA: A Multimodal Test-Time Adaptation Framework for Visual Search in the Wild},
      journal = {Under Review},
      year    = {2025},
      url     = {https://arxiv.org/abs/2505.11350},
    }

@misc{wu2024largescalecontrastivelanguageaudiopretraining,
      title={Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation}, 
      author={Yusong Wu and Ke Chen and Tianyu Zhang and Yuchen Hui and Marianna Nezhurina and Taylor Berg-Kirkpatrick and Shlomo Dubnov},
      year={2024},
      eprint={2211.06687},
      archivePrefix={arXiv},
      primaryClass={cs.SD},
      url={https://arxiv.org/abs/2211.06687}, 
}