English  |  正體中文  |  简体中文  |  全文筆數/總筆數 : 62567/95223 (66%)
造訪人次 : 2520556      線上人數 : 267
RC Version 7.0 © Powered By DSPACE, MIT. Enhanced by NTU Library & TKU Library IR team.
搜尋範圍 查詢小技巧:
  • 您可在西文檢索詞彙前後加上"雙引號",以獲取較精準的檢索結果
  • 若欲以作者姓名搜尋,建議至進階搜尋限定作者欄位,可獲得較完整資料
  • 進階搜尋
    請使用永久網址來引用或連結此文件: https://tkuir.lib.tku.edu.tw/dspace/handle/987654321/118378

    題名: Reptile Meta-Tracking
    作者: Jhang, Shang-Jhih;Tsai, Chi-Yi
    關鍵詞: Generic object tracking;visual tracking;deep learning;few-shot learning;Reptile meta-learning
    日期: 2019
    上傳時間: 2020-03-21 12:11:21 (UTC+8)
    摘要: Generic object tracking (GOT) is one of the main topics in computer vision for many years. The goal of GOT is to recognize and locate a specific object in the form of bounding box throughout a sequence of images. Moreover, GOT also requires algorithms to locate objects down to instances level. These requirements produce some unique challenges especially for deep learning based GOT algorithms that may easily become over-fitting if given a really small training dataset of the object during the online tracking process. To deal with this issue, we propose a novel Reptile meta-tracking algorithm, which adopts a first-order meta-learning technique so that during initialization, the visual tracker only requires few training examples and few steps of optimization to perform well. The proposed Reptile meta-tracker is evaluated on OTB2015 and VOT2018 tracking benchmark datasets, and outperforms several state-of-the-art trackers using one-pass evaluation.
    關聯: IEEE
    DOI: 10.1109/AVSS.2019.8909863
    顯示於類別:[電機工程學系暨研究所] 會議論文


    檔案 描述 大小格式瀏覽次數



    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library & TKU Library IR teams. Copyright ©   - 回饋