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 en_US
收錄於
會議性質 國際
校內研討會地點 無
研討會時間 20190918~20190921
通訊作者
國別 USA
公開徵稿
出版型式
出處 IEEE
相關連結

機構典藏連結 ( http://tkuir.lib.tku.edu.tw:8080/dspace/handle/987654321/118378 )

SDGS 優質教育,產業創新與基礎設施