教師資料查詢 | 類別: 會議論文 | 教師: 蔡奇謚 Chi-yi Tsai (瀏覽個人網頁)

標題:Reptile Meta-Tracking
學年108
學期1
發表日期2019/09/18
作品名稱Reptile Meta-Tracking
作品名稱(其他語言)
著者Shang-Jhih Jhang; Chi-Yi Tsai
作品所屬單位
出版者
會議名稱IEEE International Conference on Advanced Video and Signal Based Surveillance
會議地點Taipei, Taiwan
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.
關鍵字Generic object tracking;visual tracking;deep learning;few-shot learning;Reptile meta-learning
語言英文(美國)
收錄於
會議性質國際
校內研討會地點
研討會時間20190918~20190921
通訊作者
國別美國
公開徵稿
出版型式
出處IEEE
相關連結
Google+ 推薦功能,讓全世界都能看到您的推薦!