Driving behavior recognition via self-discovery learning

Autonomous driving systems require a deep understanding of human driving behaviors to achieve higher intelligence andthis http URLadvancements in deep learning, challenges such as long-tail distribution due to scarce samples and confusion from similar behaviors hinder effective driving behaviorthis http URLmethods often fail to address sample confusion adequately, as datasets frequently contain ambiguous samples that obscure unique semantic information.

@article{wang2025_2503.14194,
  title={ Driving behavior recognition via self-discovery learning },
  author={ Yilin Wang },
  journal={arXiv preprint arXiv:2503.14194},
  year={ 2025 }
}