{
  "absUrl": "https://arxiv.org/abs/2610.15342v1",
  "arxivId": "2610.15342",
  "arxivVersion": 1,
  "arxivVersionedId": "2610.15342v1",
  "authors": [
    {
      "affiliations": [
        "the School of Big Data and Statistics, Anhui University, Hefei 230039, China"
      ],
      "name": "Hanyu Xuan"
    },
    {
      "affiliations": [
        "the School of Big Data and Statistics, Anhui University, Hefei 230039, China"
      ],
      "name": "Haoran Xu"
    },
    {
      "affiliations": [
        "the School of Big Data and Statistics, Anhui University, Hefei 230039, China"
      ],
      "name": "Min Yin"
    },
    {
      "affiliations": [
        "the School of Information Science and Technology, University of Science and Technology of China, Hefei, China"
      ],
      "name": "Shuo Wang"
    },
    {
      "affiliations": [
        "the Shenzhen University Medical School, Shenzhen University, Shenzhen 518060, China"
      ],
      "name": "Cheng Zhao"
    },
    {
      "affiliations": [
        "the College of Information Technology, United Arab Emirates University, Abu Dhabi, 15551, United Arab Emirates"
      ],
      "name": "Kun Li"
    },
    {
      "affiliations": [
        "the Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, 230026, China"
      ],
      "name": "Fei Wang"
    },
    {
      "affiliations": [
        "the College of Computing and Data Science, Nanyang Technological University, Singapore 639798, Singapore"
      ],
      "name": "Zhiliang Wu"
    },
    {
      "affiliations": [
        "the Shenzhen University Medical School, Shenzhen University, Shenzhen 518060, China"
      ],
      "name": "Guanghui Yue"
    },
    {
      "affiliations": [
        "the School of Artificial Intelligence, Zhejiang University, Hangzhou 310007, China"
      ],
      "name": "Hehe Fan"
    }
  ],
  "contract": "researcher-sidecars-v1",
  "id": "2610.15342v1",
  "originalTitle": "SIMPLE: Semantic Structure-Aligned Prompt Learning for Open-Vocabulary Audio-Visual Event Localization",
  "pdfUrl": "https://arxiv.org/pdf/2610.15342v1.pdf",
  "schemaVersion": 1,
  "type": "preprint"
}