Scholarlink

Ho Chi Minh City AI Challenge 2024, now in its fifth edition, focused on advancing event retrieval techniques from large video collections, driving research and innovation in video analysis. The challenge featured a dataset of 1,471 videos spanning 328 h alongside diverse query formats to evaluate system performance in realistic scenarios. Participant teams competed in multiple rounds, addressing complex queries involving temporal and semantic event understanding. Leveraging advanced deep learning models, temporal segmentation, and multimodal fusion techniques, participants showcased innovative approaches across textual and visual Known-Item Search and Question Answering tasks. Visual KIS recorded the highest performance, highlighting the advantages of rich visual context over text-based queries. This paper provides an overview of the challenge organization, dataset, methodologies, evaluation metrics, and insights into trends and solutions observed during the competition.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Event Retrieval from Large Video Collection in Ho Chi Minh City AI Challenge 2024

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Trong-Le Do,
  • Viet-Tham Huynh,
  • Thuc Nguyen-Quang,
  • Hai-Dang Nguyen,
  • Mai-Khiem Tran,
  • Tu V. Ninh,
  • Tu-Khiem Le,
  • Thanh Duc Ngo,
  • Duc-Tien Dang-Nguyen,
  • Tu-Trinh Ngo,
  • Klaus Schöffmann,
  • Cathal Gurrin,
  • Minh-Triet Tran

摘要

Ho Chi Minh City AI Challenge 2024, now in its fifth edition, focused on advancing event retrieval techniques from large video collections, driving research and innovation in video analysis. The challenge featured a dataset of 1,471 videos spanning 328 h alongside diverse query formats to evaluate system performance in realistic scenarios. Participant teams competed in multiple rounds, addressing complex queries involving temporal and semantic event understanding. Leveraging advanced deep learning models, temporal segmentation, and multimodal fusion techniques, participants showcased innovative approaches across textual and visual Known-Item Search and Question Answering tasks. Visual KIS recorded the highest performance, highlighting the advantages of rich visual context over text-based queries. This paper provides an overview of the challenge organization, dataset, methodologies, evaluation metrics, and insights into trends and solutions observed during the competition.