Xiaobin Zhu

Dr. Xiaobin Zhu

Department of Computer Science and Technology, University of Science and Technology Beijing, Beijing, China

Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
5 June 2018 in Remote Sensing
Verified
Journal Article
Open access
PDF file
PLPeng Li
Peng Li
Peng RenPeng Ren
Peng Ren
XZXiao-Yu Zhang
Xiao-Yu Zhang
QWQian Wang
Qian Wang
Xiaobin ZhuXiaobin Zhu
Xiaobin Zhu
LWLei Wang
Lei Wang
Effective feature representations play an important role in remote sensing image analysis tasks. With the rapid progress of deep learning techniques, deep features have been widely applied to remote sensing image understanding in recent years and shown powerful ability in image representation. The existing deep feature extraction approaches are usually carried out on the whole image directly. However, such deep feature representation strategies may not effectively capture the local geometric invariance of target regions in remote sensing images. In this paper, we propose a novel region-wise deep feature extraction framework for remote sensing images. First, regions that may contain the target information are extracted from one whole image. Then, these regions are fed into a pre-trained convolutional neural network (CNN) model to extract regional deep features. Finally, the regional deep features are encoded by an improved Vector of Locally Aggregated Descriptors (VLAD) algorithm to generate the feature representation for the image. We conducted extensive experiments on remote sensing image classification and retrieval tasks based on the proposed region-wise deep feature extraction framework. The comparison results show that the proposed approach is superior to the existing CNN feature extraction methods.

1 August 2015 in Neurocomputing
Verified
Journal Article
Closed access
XZXiao-Yu Zhang
Xiao-Yu Zhang
SWShupeng Wang
Shupeng Wang
Xiaobin ZhuXiaobin Zhu
Xiaobin Zhu
XYXiaochun Yun
Xiaochun Yun
GWGuangjun Wu
Guangjun Wu
YWYipeng Wang
Yipeng Wang

4 May 2018 in Remote Sensing
Verified
Journal Article
Open access
PDF file
PLPeng Li
Peng Li
XZXiao-Yu Zhang
Xiao-Yu Zhang
Xiaobin ZhuXiaobin Zhu
Xiaobin Zhu
Peng RenPeng Ren
Peng Ren
Recently, hashing-based large-scale remote sensing (RS) image retrieval has attracted much attention. Many new hashing algorithms have been developed and successfully applied to fast RS image retrieval tasks. However, there exists an important problem rarely addressed in the research literature of RS image hashing. The RS images are practically produced in a streaming manner in many real-world applications, which means the data distribution keeps changing over time. Most existing RS image hashing methods are batch-based models whose hash functions are learned once for all and kept fixed all the time. Therefore, the pre-trained hash functions might not fit the ever-growing new RS images. Moreover, the batch-based models have to load all the training images into memory for model learning, which consumes many computing and memory resources. To address the above deficiencies, we propose a new online hashing method, which learns and adapts its hashing functions with respect to the newly incoming RS images in terms of a novel online partial random learning scheme. Our hash model is updated in a sequential mode such that the representative power of the learned binary codes for RS images are improved accordingly. Moreover, benefiting from the online learning strategy, our proposed hashing approach is quite suitable for scalable real-world remote sensing image retrieval. Extensive experiments on two large-scale RS image databases under online setting demonstrated the efficacy and effectiveness of the proposed method.

1 November 2016 in Information Sciences
Verified
Journal Article
Closed access
CZChunjie Zhang
Chunjie Zhang
ZXZhe Xue
Zhe Xue
Xiaobin ZhuXiaobin Zhu
Xiaobin Zhu
HWHuanian Wang
Huanian Wang
QHQingming Huang
Qingming Huang
QTQi Tian
Qi Tian

7 June 2018 in Journal of Ambient Intelligence and Humanized Computing
Verified
Journal Article
Closed access
PDF file
Xiaobin ZhuXiaobin Zhu
Xiaobin Zhu
QWQian Wang
Qian Wang
PLPeng Li
Peng Li
XZXiao-Yu Zhang
Xiao-Yu Zhang
LWLei Wang
Lei Wang

27 November 2019 in arXiv
Verified
Preprint
Open access
PDF file
XZXiao-Yu Zhang
Xiao-Yu Zhang
CLChangsheng Li
Changsheng Li
HSHaichao Shi
Haichao Shi
Xiaobin ZhuXiaobin Zhu
Xiaobin Zhu
PLPeng Li
Peng Li
JDJing Dong
Jing Dong
The point process is a solid framework to model sequential data, such as videos, by exploring the underlying relevance. As a challenging problem for high-level video understanding, weakly supervised action recognition and localization in untrimmed videos has attracted intensive research attention. Knowledge transfer by leveraging the publicly available trimmed videos as external guidance is a promising attempt to make up for the coarse-grained video-level annotation and improve the generalization performance. However, unconstrained knowledge transfer may bring about irrelevant noise and jeopardize the learning model. This paper proposes a novel adaptability decomposing encoder-decoder network to transfer reliable knowledge between trimmed and untrimmed videos for action recognition and localization via bidirectional point process modeling, given only video-level annotations. By decomposing the original features into domain-adaptable and domain-specific ones based on their adaptability, trimmed-untrimmed knowledge transfer can be safely confined within a more coherent subspace. An encoder-decoder based structure is carefully designed and jointly optimized to facilitate effective action classification and temporal localization. Extensive experiments are conducted on two benchmark datasets (i.e., THUMOS14 and ActivityNet1.3), and experimental results clearly corroborate the efficacy of our method.