Xiaobin Zhu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Xiaobin Zhu has a total of 21 co-authors. Here are the top co-authors by number of shared publications:
- Xiao-Yu Zhang
Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China
4 shared publications - Peng Li
College of Electrical Engineering and New Energy, China Three Gorges University, Yichang 443002, China
3 shared publications - Peng Ren
China University of Petroleum (East China)
2 shared publications - Changsheng Li
School of Mechatronical Engineering Beijing Institute of Technology Beijing China
1 shared publication - Chunjie Zhang
Institute of Information Science, School of Computer Science and Technology, Beijing Jiaotong University, Beijing 100044, China
1 shared publication - Guangjun Wu
Chinese Academy of Sciences
1 shared publication
Latest Publications
- Open Access
AdapNet: Adaptability Decomposing Encoder-Decoder Network for Weakly Supervised Action Recognition and Localization
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.
Open AccessAdapNet: Adaptability Decomposing Encoder-Decoder Network for Weakly Supervised Action Recognition and Localization
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.
- 7 June 2018
- Published by Springer Nature in Journal of Ambient Intelligence and Humanized Computing
- Vol. 14 (11) , 14775-14784
Learning region-wise deep feature representation for image analysis
- 7 June 2018
- Published by Springer Nature in Journal of Ambient Intelligence and Humanized Computing
- Vol. 14 (11) , 14775-14784
Learning region-wise deep feature representation for image analysis
- Open Access
- 5 June 2018
- Published by MDPI AG in Remote Sensing
- Vol. 10 (6) , 871
Region-Wise Deep Feature Representation for Remote Sensing Images
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.
- 5 June 2018
- Published by MDPI AG in Remote Sensing
- Vol. 10 (6) , 871
Open AccessRegion-Wise Deep Feature Representation for Remote Sensing Images
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.
- Open Access
- 4 May 2018
- Published by MDPI AG in Remote Sensing
- Vol. 10 (5) , 709
Online Hashing for Scalable Remote Sensing Image Retrieval
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.
- 4 May 2018
- Published by MDPI AG in Remote Sensing
- Vol. 10 (5) , 709
Open AccessOnline Hashing for Scalable Remote Sensing Image Retrieval
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
- Published by Elsevier in Information Sciences
- Vol. 369, 160-170
Boosted random contextual semantic space based representation for visual recognition
- 1 November 2016
- Published by Elsevier in Information Sciences
- Vol. 369, 160-170
Boosted random contextual semantic space based representation for visual recognition
- 1 August 2015
- Published by Elsevier in Neurocomputing
- Vol. 162, 163-170
Update vs. upgrade: Modeling with indeterminate multi-class active learning
- 1 August 2015
- Published by Elsevier in Neurocomputing
- Vol. 162, 163-170
Update vs. upgrade: Modeling with indeterminate multi-class active learning