{
  "absUrl": "https://arxiv.org/abs/2609.23376v1",
  "arxivId": "2609.23376",
  "arxivVersion": 1,
  "arxivVersionedId": "2609.23376v1",
  "authors": [
    {
      "affiliations": [
        "Tongji University, Shanghai, China"
      ],
      "name": "Yi Xu"
    },
    {
      "affiliations": [
        "Tongji University, Shanghai, China"
      ],
      "name": "Cheng Chen"
    },
    {
      "affiliations": [
        "Tongji University, Shanghai, China"
      ],
      "name": "Wenzhuo Lei"
    }
  ],
  "contract": "researcher-sidecars-v1",
  "id": "2609.23376v1",
  "originalTitle": "If You Hear It, Help Find It: Orthogonal Knowledge Distillation for Open-Vocabulary Audio-Visual Event Localization",
  "pdfUrl": "https://arxiv.org/pdf/2609.23376v1.pdf",
  "schemaVersion": 1,
  "type": "preprint"
}