Jun 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
Research Subjects
Jun Zhu has a total of 17 co-authors. Here are the top co-authors by number of shared publications:
- Alan Yuille
Johns Hopkins University
2 shared publications - Cihang Xie
Johns Hopkins University
2 shared publications - Jianyu Wang
Baidu Research Sunnyvale USA
2 shared publications - Lingxi Xie
HuaWei Inc., Shenzhen, China
2 shared publications - Zhishuai Zhang
Johns Hopkins University
2 shared publications - Jun Huang
Shanghai Advanced Research Institute, Chinese Academy of Sciences, Shanghai, China
1 shared publication
Latest Publications
- Open Access
- 1 January 2018
- Published by International Press of Boston in Annals of Mathematical Sciences and Applications
- Vol. 3 (1) , 151-188
Visual concepts and compositional voting
International Press of Boston - publishers of scholarly mathematical and scientific journals and books
- 1 January 2018
- Published by International Press of Boston in Annals of Mathematical Sciences and Applications
- Vol. 3 (1) , 151-188
Open AccessVisual concepts and compositional voting
International Press of Boston - publishers of scholarly mathematical and scientific journals and books
- Open Access
Detecting Semantic Parts on Partially Occluded Objects
In this paper, we address the task of detecting semantic parts on partially occluded objects. We consider a scenario where the model is trained using non-occluded images but tested on occluded images. The motivation is that there are infinite number of occlusion patterns in real world, which cannot be fully covered in the training data. So the models should be inherently robust and adaptive to occlusions instead of fitting / learning the occlusion patterns in the training data. Our approach detects semantic parts by accumulating the confidence of local visual cues. Specifically, the method uses a simple voting method, based on log-likelihood ratio tests and spatial constraints, to combine the evidence of local cues. These cues are called visual concepts, which are derived by clustering the internal states of deep networks. We evaluate our voting scheme on the VehicleSemanticPart dataset with dense part annotations. We randomly place two, three or four irrelevant objects onto the target object to generate testing images with various occlusions. Experiments show that our algorithm outperforms several competitors in semantic part detection when occlusions are present.
Open AccessDetecting Semantic Parts on Partially Occluded Objects
In this paper, we address the task of detecting semantic parts on partially occluded objects. We consider a scenario where the model is trained using non-occluded images but tested on occluded images. The motivation is that there are infinite number of occlusion patterns in real world, which cannot be fully covered in the training data. So the models should be inherently robust and adaptive to occlusions instead of fitting / learning the occlusion patterns in the training data. Our approach detects semantic parts by accumulating the confidence of local visual cues. Specifically, the method uses a simple voting method, based on log-likelihood ratio tests and spatial constraints, to combine the evidence of local cues. These cues are called visual concepts, which are derived by clustering the internal states of deep networks. We evaluate our voting scheme on the VehicleSemanticPart dataset with dense part annotations. We randomly place two, three or four irrelevant objects onto the target object to generate testing images with various occlusions. Experiments show that our algorithm outperforms several competitors in semantic part detection when occlusions are present.
- 2 May 2014
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 16 (15209210) , 1
Contextual Object Detection With Spatial Context Prototypes
Contextual information is widely exploited in state-of-the-art object detection systems, most of which utilize pre-defined spatial relationships (e.g., above, below, next to, etc.). However, we observe that the spatial arrangement manifests heterogeneous statistical distributions for different object class pairs, which suggests mining class-specified prototypes of spatial contexts in a data-driven manner. This paper proposes a novel contrast K-Means clustering algorithm for automatically discovering spatial context prototypes to beyond the pre-defined spatial relationship representation in literature. Based on the learned prototypes, we further construct the spatial context features by using a simple localized soft assignment quantization method. Besides, considering the large number of real object categories that might lead to overcomplicated spatial context features, we propose a feature refinement method based on the number of context occurrences and K-L divergence to efficiently reduce the complexity of our contextual model. The experiment results on PASCAL VOC dataset and SUN 09 dataset demonstrate that our method can effectively capture meaningful spatial context prototypes as well as most contributing contextual features for different object class pairs and thus boost recognition performance on object detection task.
- 2 May 2014
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 16 (15209210) , 1
Contextual Object Detection With Spatial Context Prototypes
Contextual information is widely exploited in state-of-the-art object detection systems, most of which utilize pre-defined spatial relationships (e.g., above, below, next to, etc.). However, we observe that the spatial arrangement manifests heterogeneous statistical distributions for different object class pairs, which suggests mining class-specified prototypes of spatial contexts in a data-driven manner. This paper proposes a novel contrast K-Means clustering algorithm for automatically discovering spatial context prototypes to beyond the pre-defined spatial relationship representation in literature. Based on the learned prototypes, we further construct the spatial context features by using a simple localized soft assignment quantization method. Besides, considering the large number of real object categories that might lead to overcomplicated spatial context features, we propose a feature refinement method based on the number of context occurrences and K-L divergence to efficiently reduce the complexity of our contextual model. The experiment results on PASCAL VOC dataset and SUN 09 dataset demonstrate that our method can effectively capture meaningful spatial context prototypes as well as most contributing contextual features for different object class pairs and thus boost recognition performance on object detection task.
- Open Access
A Generalized Pyramid Matching Kernel for Human Action Recognition in Realistic Videos
Human action recognition is an increasingly important research topic in the fields of video sensing, analysis and understanding. Caused by unconstrained sensing conditions, there exist large intra-class variations and inter-class ambiguities in realistic videos, which hinder the improvement of recognition performance for recent vision-based action recognition systems. In this paper, we propose a generalized pyramid matching kernel (GPMK) for recognizing human actions in realistic videos, based on a multi-channel “bag of words” representation constructed from local spatial-temporal features of video clips. As an extension to the spatial-temporal pyramid matching (STPM) kernel, the GPMK leverages heterogeneous visual cues in multiple feature descriptor types and spatial-temporal grid granularity levels, to build a valid similarity metric between two video clips for kernel-based classification. Instead of the predefined and fixed weights used in STPM, we present a simple, yet effective, method to compute adaptive channel weights of GPMK based on the kernel target alignment from training data. It incorporates prior knowledge and the data-driven information of different channels in a principled way. The experimental results on three challenging video datasets (i.e., Hollywood2, Youtube and HMDB51) validate the superiority of our GPMK w.r.t. the traditional STPM kernel for realistic human action recognition and outperform the state-of-the-art results in the literature.
Open AccessA Generalized Pyramid Matching Kernel for Human Action Recognition in Realistic Videos
Human action recognition is an increasingly important research topic in the fields of video sensing, analysis and understanding. Caused by unconstrained sensing conditions, there exist large intra-class variations and inter-class ambiguities in realistic videos, which hinder the improvement of recognition performance for recent vision-based action recognition systems. In this paper, we propose a generalized pyramid matching kernel (GPMK) for recognizing human actions in realistic videos, based on a multi-channel “bag of words” representation constructed from local spatial-temporal features of video clips. As an extension to the spatial-temporal pyramid matching (STPM) kernel, the GPMK leverages heterogeneous visual cues in multiple feature descriptor types and spatial-temporal grid granularity levels, to build a valid similarity metric between two video clips for kernel-based classification. Instead of the predefined and fixed weights used in STPM, we present a simple, yet effective, method to compute adaptive channel weights of GPMK based on the kernel target alignment from training data. It incorporates prior knowledge and the data-driven information of different channels in a principled way. The experimental results on three challenging video datasets (i.e., Hollywood2, Youtube and HMDB51) validate the superiority of our GPMK w.r.t. the traditional STPM kernel for realistic human action recognition and outperform the state-of-the-art results in the literature.
- 20 June 2013
- Published by Springer Nature in Journal of Signal Processing Systems
- Vol. 74 (1) , 33-46
Top-Down Saliency Detection via Contextual Pooling
- 20 June 2013
- Published by Springer Nature in Journal of Signal Processing Systems
- Vol. 74 (1) , 33-46
Top-Down Saliency Detection via Contextual Pooling