{
  "absUrl": "https://arxiv.org/abs/2609.32180v1",
  "arxivId": "2609.32180",
  "arxivVersion": 1,
  "arxivVersionedId": "2609.32180v1",
  "authors": [
    {
      "affiliations": [
        "机构信息未在 arXiv HTML 中可靠披露"
      ],
      "name": "Saijun Wang"
    },
    {
      "affiliations": [
        "机构信息未在 arXiv HTML 中可靠披露"
      ],
      "name": "Guanfeng Tang"
    },
    {
      "affiliations": [
        "机构信息未在 arXiv HTML 中可靠披露"
      ],
      "name": "Hongbo Zhao"
    },
    {
      "affiliations": [
        "机构信息未在 arXiv HTML 中可靠披露"
      ],
      "name": "Zhicheng Lei"
    },
    {
      "affiliations": [
        "机构信息未在 arXiv HTML 中可靠披露"
      ],
      "name": "Yutong Zhang"
    },
    {
      "affiliations": [
        "机构信息未在 arXiv HTML 中可靠披露"
      ],
      "name": "Wei Ye"
    },
    {
      "affiliations": [
        "organization=College of Electronic and Information Engineering, Tongji University, Shanghai 201804, China",
        "organization=College of Electronic and Information Engineering, Shanghai Institute of Intelligent Science and Technology, State Key Laboratory of Autonomous Intelligent Unmanned Systems, Tongji University, Shanghai 201804, China"
      ],
      "name": "Rui Fan"
    }
  ],
  "contract": "researcher-sidecars-v1",
  "id": "2609.32180v1",
  "originalTitle": "Binaural Audio-Visual Instance Segmentation",
  "pdfUrl": "https://arxiv.org/pdf/2609.32180v1.pdf",
  "schemaVersion": 1,
  "type": "preprint"
}